From 80d869234df768679e211b9b37c0da96fbe8bfab Mon Sep 17 00:00:00 2001 From: maramhasanain Date: Mon, 4 Sep 2023 17:23:57 +0300 Subject: [PATCH] renamed datasets and assets --- ...=> CT22Attentionworthy_BLOOMZ_ZeroShot.py} | 4 +-- ... => CT22Attentionworthy_GPT35_ZeroShot.py} | 4 +-- ...py => CT22Attentionworthy_GPT4_FewShot.py} | 4 +-- ...y => CT22Attentionworthy_GPT4_ZeroShot.py} | 4 +-- ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ... => CT22Checkworthiness_GPT35_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ...roShot.py => CT22Claim_BLOOMZ_ZeroShot.py} | 4 +-- ...eroShot.py => CT22Claim_GPT35_ZeroShot.py} | 4 +-- ...4_FewShot.py => CT22Claim_GPT4_FewShot.py} | 4 +-- ...ZeroShot.py => CT22Claim_GPT4_ZeroShot.py} | 4 +-- ...y => COVID19Factuality_BLOOMZ_ZeroShot.py} | 4 +-- ...t.py => COVID19Factuality_GPT4_FewShot.py} | 4 +-- ....py => COVID19Factuality_GPT4_ZeroShot.py} | 4 +-- ...Shot.py => CT22Harmful_BLOOMZ_ZeroShot.py} | 4 +-- ...oShot.py => CT22Harmful_GPT35_ZeroShot.py} | 4 +-- ...FewShot.py => CT22Harmful_GPT4_FewShot.py} | 4 +-- ...roShot.py => CT22Harmful_GPT4_ZeroShot.py} | 4 +-- ...roShot.py => WANLP22T3_BLOOMZ_ZeroShot.py} | 4 +-- ...eroShot.py => WANLP22T3_GPT35_ZeroShot.py} | 4 +-- ...4_FewShot.py => WANLP22T3_GPT4_FewShot.py} | 4 +-- ...ZeroShot.py => WANLP22T3_GPT4_ZeroShot.py} | 4 +-- ...py => CT23Subjectivity_BLOOMZ_ZeroShot.py} | 0 ....py => CT23Subjectivity_GPT35_ZeroShot.py} | 0 ...ot.py => CT23Subjectivity_GPT4_FewShot.py} | 0 ...t.py => CT23Subjectivity_GPT4_ZeroShot.py} | 0 ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ... SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} | 8 ++--- ... => SemEval23T3Propaganda_GPT4_FewShot.py} | 8 ++--- ...=> SemEval23T3Propaganda_GPT4_ZeroShot.py} | 8 ++--- ...=> CT22Checkworthiness_BLOOMZ_ZeroShot.py} | 4 +-- ...py => CT22Checkworthiness_GPT4_FewShot.py} | 4 +-- ...y => CT22Checkworthiness_GPT4_ZeroShot.py} | 4 +-- ...tualityCOVID19.py => COVID19Factuality.py} | 0 ...entionworthy.py => CT22Attentionworthy.py} | 2 +- ...ckworthiness.py => CT22Checkworthiness.py} | 2 +- llmebench/datasets/{Claim.py => CT22Claim.py} | 8 ++--- .../datasets/{Harmful.py => CT22Harmful.py} | 0 .../{Subjectivity.py => CT23Subjectivity.py} | 0 ...aSemEval23.py => SemEval23T3Propaganda.py} | 7 ++--- .../{Propaganda.py => WANLP22T3Propaganda.py} | 13 ++++++--- ...elSemEval23.py => MultilabelPropaganda.py} | 6 ++-- llmebench/tasks/PropagandaMultilabel.py | 29 ------------------- llmebench/tasks/Subjectivity.py | 4 +-- 71 files changed, 169 insertions(+), 198 deletions(-) rename assets/ar/factuality_disinformation_harmful_content/attentionworthy/{Attentionworthy_BLOOMZ_ZeroShot.py => CT22Attentionworthy_BLOOMZ_ZeroShot.py} (93%) rename assets/ar/factuality_disinformation_harmful_content/attentionworthy/{Attentionworthy_GPT35_ZeroShot.py => CT22Attentionworthy_GPT35_ZeroShot.py} (95%) rename assets/ar/factuality_disinformation_harmful_content/attentionworthy/{Attentionworthy_GPT4_FewShot.py => CT22Attentionworthy_GPT4_FewShot.py} (97%) rename assets/ar/factuality_disinformation_harmful_content/attentionworthy/{Attentionworthy_GPT4_ZeroShot.py => CT22Attentionworthy_GPT4_ZeroShot.py} (95%) rename assets/ar/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (92%) rename assets/ar/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT35_ZeroShot.py => CT22Checkworthiness_GPT35_ZeroShot.py} (93%) rename assets/ar/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/ar/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename assets/ar/factuality_disinformation_harmful_content/claim_detection/{ClaimDetectCOVID19_BLOOMZ_ZeroShot.py => CT22Claim_BLOOMZ_ZeroShot.py} (93%) rename assets/ar/factuality_disinformation_harmful_content/claim_detection/{ClaimDetectCOVID19_GPT35_ZeroShot.py => CT22Claim_GPT35_ZeroShot.py} (94%) rename assets/ar/factuality_disinformation_harmful_content/claim_detection/{ClaimDetectCOVID19_GPT4_FewShot.py => CT22Claim_GPT4_FewShot.py} (96%) rename assets/ar/factuality_disinformation_harmful_content/claim_detection/{ClaimDetectCOVID19_GPT4_ZeroShot.py => CT22Claim_GPT4_ZeroShot.py} (94%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityCOVID19_BLOOMZ_ZeroShot.py => COVID19Factuality_BLOOMZ_ZeroShot.py} (93%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityCOVID19_GPT4_FewShot.py => COVID19Factuality_GPT4_FewShot.py} (96%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityCOVID19_GPT4_ZeroShot.py => COVID19Factuality_GPT4_ZeroShot.py} (94%) rename assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/{HarmfulDetectCOVID19_BLOOMZ_ZeroShot.py => CT22Harmful_BLOOMZ_ZeroShot.py} (94%) rename assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/{HarmfulDetectCOVID19_GPT35_ZeroShot.py => CT22Harmful_GPT35_ZeroShot.py} (94%) rename assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/{HarmfulDetectCOVID19_GPT4_FewShot.py => CT22Harmful_GPT4_FewShot.py} (96%) rename assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/{HarmfulDetectCOVID19_GPT4_ZeroShot.py => CT22Harmful_GPT4_ZeroShot.py} (96%) rename assets/ar/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => WANLP22T3_BLOOMZ_ZeroShot.py} (98%) rename assets/ar/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT35_ZeroShot.py => WANLP22T3_GPT35_ZeroShot.py} (97%) rename assets/ar/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => WANLP22T3_GPT4_FewShot.py} (97%) rename assets/ar/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => WANLP22T3_GPT4_ZeroShot.py} (98%) rename assets/ar/factuality_disinformation_harmful_content/subjectivity/{Subjectivity_BLOOMZ_ZeroShot.py => CT23Subjectivity_BLOOMZ_ZeroShot.py} (100%) rename assets/ar/factuality_disinformation_harmful_content/subjectivity/{Subjectivity_GPT35_ZeroShot.py => CT23Subjectivity_GPT35_ZeroShot.py} (100%) rename assets/ar/factuality_disinformation_harmful_content/subjectivity/{Subjectivity_GPT4_FewShot.py => CT23Subjectivity_GPT4_FewShot.py} (100%) rename assets/ar/factuality_disinformation_harmful_content/subjectivity/{Subjectivity_GPT4_ZeroShot.py => CT23Subjectivity_GPT4_ZeroShot.py} (100%) rename assets/bg/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (92%) rename assets/bg/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/bg/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename assets/de/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/de/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/de/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/en/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (92%) rename assets/en/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/en/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename assets/en/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/en/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/en/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/es/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (91%) rename assets/es/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/es/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename assets/fr/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/fr/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/fr/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/it/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/it/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/it/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/nl/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (92%) rename assets/nl/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/nl/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename assets/pl/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/pl/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/pl/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/ru/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_BLOOMZ_ZeroShot.py => SemEval23T3Propaganda_BLOOMZ_ZeroShot.py} (96%) rename assets/ru/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_FewShot.py => SemEval23T3Propaganda_GPT4_FewShot.py} (97%) rename assets/ru/factuality_disinformation_harmful_content/propaganda/{PropMultilabel_GPT4_ZeroShot.py => SemEval23T3Propaganda_GPT4_ZeroShot.py} (97%) rename assets/tr/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_BLOOMZ_ZeroShot.py => CT22Checkworthiness_BLOOMZ_ZeroShot.py} (91%) rename assets/tr/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_FewShot.py => CT22Checkworthiness_GPT4_FewShot.py} (96%) rename assets/tr/factuality_disinformation_harmful_content/checkworthyness/{Checkworthiness_GPT4_ZeroShot.py => CT22Checkworthiness_GPT4_ZeroShot.py} (95%) rename llmebench/datasets/{FactualityCOVID19.py => COVID19Factuality.py} (100%) rename llmebench/datasets/{Attentionworthy.py => CT22Attentionworthy.py} (96%) rename llmebench/datasets/{Checkworthiness.py => CT22Checkworthiness.py} (97%) rename llmebench/datasets/{Claim.py => CT22Claim.py} (90%) rename llmebench/datasets/{Harmful.py => CT22Harmful.py} (100%) rename llmebench/datasets/{Subjectivity.py => CT23Subjectivity.py} (100%) rename llmebench/datasets/{PropagandaSemEval23.py => SemEval23T3Propaganda.py} (95%) rename llmebench/datasets/{Propaganda.py => WANLP22T3Propaganda.py} (76%) rename llmebench/tasks/{PropagandaMultilabelSemEval23.py => MultilabelPropaganda.py} (86%) delete mode 100644 llmebench/tasks/PropagandaMultilabel.py diff --git a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_BLOOMZ_ZeroShot.py similarity index 93% rename from assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_BLOOMZ_ZeroShot.py index 37f15dde..de9d63a1 100644 --- a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import AttentionworthyDataset +from llmebench.datasets import CT22AttentionworthyDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import AttentionworthyTask def config(): return { - "dataset": AttentionworthyDataset, + "dataset": CT22AttentionworthyDataset, "dataset_args": {}, "task": AttentionworthyTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT35_ZeroShot.py similarity index 95% rename from assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT35_ZeroShot.py index 23d7f66c..1e13fbc5 100644 --- a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT35_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import AttentionworthyDataset +from llmebench.datasets import CT22AttentionworthyDataset from llmebench.models import GPTModel, RandomGPTModel from llmebench.tasks import AttentionworthyTask def config(): return { - "dataset": AttentionworthyDataset, + "dataset": CT22AttentionworthyDataset, "dataset_args": {}, "task": AttentionworthyTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_FewShot.py similarity index 97% rename from assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_FewShot.py index 92c7a32b..dc9355fd 100644 --- a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_FewShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import AttentionworthyDataset +from llmebench.datasets import CT22AttentionworthyDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import AttentionworthyTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": AttentionworthyDataset, + "dataset": CT22AttentionworthyDataset, "dataset_args": {}, "task": AttentionworthyTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_ZeroShot.py similarity index 95% rename from assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_ZeroShot.py index 69da7868..82f465f7 100644 --- a/assets/ar/factuality_disinformation_harmful_content/attentionworthy/Attentionworthy_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/attentionworthy/CT22Attentionworthy_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import AttentionworthyDataset +from llmebench.datasets import CT22AttentionworthyDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import AttentionworthyTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": AttentionworthyDataset, + "dataset": CT22AttentionworthyDataset, "dataset_args": {}, "task": AttentionworthyTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 92% rename from assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index 7d7c512f..4b852302 100644 --- a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT35_ZeroShot.py similarity index 93% rename from assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT35_ZeroShot.py index 5e60e8a5..ec0d9a82 100644 --- a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT35_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTModel, RandomGPTModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index 444fb4de..85c628f8 100644 --- a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index d90cb0ce..60f3b7d5 100644 --- a/assets/ar/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_BLOOMZ_ZeroShot.py similarity index 93% rename from assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_BLOOMZ_ZeroShot.py index 63be543d..4e171616 100644 --- a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidClaimDataset +from llmebench.datasets import CT22ClaimDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import ClaimDetectionTask def config(): return { - "dataset": CovidClaimDataset, + "dataset": CT22ClaimDataset, "dataset_args": {}, "task": ClaimDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT35_ZeroShot.py similarity index 94% rename from assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT35_ZeroShot.py index f8e2ba13..64a027ea 100644 --- a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT35_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidClaimDataset +from llmebench.datasets import CT22ClaimDataset from llmebench.models import GPTModel from llmebench.tasks import ClaimDetectionTask def config(): return { - "dataset": CovidClaimDataset, + "dataset": CT22ClaimDataset, "dataset_args": {}, "task": ClaimDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_FewShot.py similarity index 96% rename from assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_FewShot.py index 8ed99f9a..6059c977 100644 --- a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_FewShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidClaimDataset +from llmebench.datasets import CT22ClaimDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import ClaimDetectionTask def config(): return { - "dataset": CovidClaimDataset, + "dataset": CT22ClaimDataset, "dataset_args": {}, "task": ClaimDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_ZeroShot.py similarity index 94% rename from assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_ZeroShot.py index 1e9c3c73..e2112584 100644 --- a/assets/ar/factuality_disinformation_harmful_content/claim_detection/ClaimDetectCOVID19_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/claim_detection/CT22Claim_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_BLOOMZ_ZeroShot.py similarity index 93% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_BLOOMZ_ZeroShot.py index fa4dc0dd..ce18ac41 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import FactualityCOVID19Dataset +from llmebench.datasets import COVID19FactualityDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import FactualityCOVID19Task def config(): return { - "dataset": FactualityCOVID19Dataset, + "dataset": COVID19FactualityDataset, "dataset_args": {}, "task": FactualityCOVID19Task, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_FewShot.py similarity index 96% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_FewShot.py index e165251a..1d835f46 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_FewShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import FactualityCOVID19Dataset +from llmebench.datasets import COVID19FactualityDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import FactualityCOVID19Task @@ -12,7 +12,7 @@ def config(): return { - "dataset": FactualityCOVID19Dataset, + "dataset": COVID19FactualityDataset, "dataset_args": {}, "task": FactualityCOVID19Task, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_ZeroShot.py similarity index 94% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_ZeroShot.py index 6b74eb7e..94d2f1fd 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityCOVID19_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/COVID19Factuality_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import FactualityCOVID19Dataset +from llmebench.datasets import COVID19FactualityDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import FactualityCOVID19Task @@ -12,7 +12,7 @@ def config(): return { - "dataset": FactualityCOVID19Dataset, + "dataset": COVID19FactualityDataset, "dataset_args": {}, "task": FactualityCOVID19Task, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_BLOOMZ_ZeroShot.py similarity index 94% rename from assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_BLOOMZ_ZeroShot.py index 20cb07f7..ac1040ae 100644 --- a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidHarmfulDataset +from llmebench.datasets import CT22HarmfulDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import HarmfulDetectionTask def config(): return { - "dataset": CovidHarmfulDataset, + "dataset": CT22HarmfulDataset, "dataset_args": {}, "task": HarmfulDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT35_ZeroShot.py similarity index 94% rename from assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT35_ZeroShot.py index 8db951ae..b2f6696f 100644 --- a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT35_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidHarmfulDataset +from llmebench.datasets import CT22HarmfulDataset from llmebench.models import GPTModel from llmebench.tasks import HarmfulDetectionTask def config(): return { - "dataset": CovidHarmfulDataset, + "dataset": CT22HarmfulDataset, "dataset_args": {}, "task": HarmfulDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_FewShot.py similarity index 96% rename from assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_FewShot.py index fe497189..92cdce83 100644 --- a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_FewShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CovidHarmfulDataset +from llmebench.datasets import CT22HarmfulDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import HarmfulDetectionTask def config(): return { - "dataset": CovidHarmfulDataset, + "dataset": CT22HarmfulDataset, "dataset_args": {}, "task": HarmfulDetectionTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_ZeroShot.py similarity index 96% rename from assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_ZeroShot.py index 8b0813b0..3779a9d6 100644 --- a/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/HarmfulDetectCOVID19_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/harmfulness_detection/CT22Harmful_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_BLOOMZ_ZeroShot.py similarity index 98% rename from assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_BLOOMZ_ZeroShot.py index 0247eaa6..fd36a6a6 100644 --- a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_BLOOMZ_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import PropagandaTweetDataset +from llmebench.datasets import WANLP22PropagandaDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import PropagandaMultilabelTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": PropagandaTweetDataset, + "dataset": WANLP22PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda/classes.txt" }, diff --git a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT35_ZeroShot.py similarity index 97% rename from assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT35_ZeroShot.py index b9ad7f81..873833b7 100644 --- a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT35_ZeroShot.py @@ -2,14 +2,14 @@ import regex as re -from llmebench.datasets import PropagandaTweetDataset +from llmebench.datasets import WANLP22PropagandaDataset from llmebench.models import GPTModel from llmebench.tasks import PropagandaMultilabelTask def config(): return { - "dataset": PropagandaTweetDataset, + "dataset": WANLP22PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda/classes.txt" }, diff --git a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_FewShot.py similarity index 97% rename from assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_FewShot.py index 0b1f913b..e43084d8 100644 --- a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_FewShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import PropagandaTweetDataset +from llmebench.datasets import WANLP22PropagandaDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import PropagandaMultilabelTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": PropagandaTweetDataset, + "dataset": WANLP22PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda/classes.txt" }, diff --git a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_ZeroShot.py similarity index 98% rename from assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_ZeroShot.py index 271385fe..d5e1a6cf 100644 --- a/assets/ar/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/propaganda/WANLP22T3_GPT4_ZeroShot.py @@ -2,7 +2,7 @@ import random import re -from llmebench.datasets import PropagandaTweetDataset +from llmebench.datasets import WANLP22T3Dataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import PropagandaMultilabelTask @@ -12,7 +12,7 @@ def config(): return { - "dataset": PropagandaTweetDataset, + "dataset": WANLP22T3Dataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda/classes.txt" }, diff --git a/assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_BLOOMZ_ZeroShot.py similarity index 100% rename from assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_BLOOMZ_ZeroShot.py diff --git a/assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT35_ZeroShot.py similarity index 100% rename from assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT35_ZeroShot.py diff --git a/assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT4_FewShot.py similarity index 100% rename from assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT4_FewShot.py diff --git a/assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT4_ZeroShot.py similarity index 100% rename from assets/ar/factuality_disinformation_harmful_content/subjectivity/Subjectivity_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/subjectivity/CT23Subjectivity_GPT4_ZeroShot.py diff --git a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 92% rename from assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index 10c2a3bf..ff303850 100644 --- a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index 495d05d2..37cfbea5 100644 --- a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index 2d118f14..408435e3 100644 --- a/assets/bg/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/bg/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index 7f38863d..f49e669f 100644 --- a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index 70523f8e..0c464fb3 100644 --- a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index e7836e14..aea9d3f9 100644 --- a/assets/de/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/de/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 92% rename from assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index 5bf0e294..296280ce 100644 --- a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index d0b67175..bf4b0537 100644 --- a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index 8cb18b32..fa4d5af5 100644 --- a/assets/en/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/en/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index 6fa517a7..904c14e3 100644 --- a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index e7f33f39..624f3318 100644 --- a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index 590ca1ab..659e6faa 100644 --- a/assets/en/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/en/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 91% rename from assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index d8c1a989..977f9864 100644 --- a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index e6099674..0f5c195f 100644 --- a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index 3ed072e6..bb7c65fd 100644 --- a/assets/es/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/es/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index cc58c362..f3b2dd9c 100644 --- a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index 2c642c7f..7f49bd7b 100644 --- a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index 6c7c4dc7..ae106b5c 100644 --- a/assets/fr/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/fr/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index 9103c03c..711ce596 100644 --- a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index 2b782ca3..8359def4 100644 --- a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index 511ca715..8e939b86 100644 --- a/assets/it/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/it/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 92% rename from assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index 06793d52..c373d29d 100644 --- a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index 7f241509..a7677af1 100644 --- a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index f52b350c..4caf1405 100644 --- a/assets/nl/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/nl/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index 4fca8321..b8cf551e 100644 --- a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index d9447aaa..de992641 100644 --- a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index cc0a834b..1d7886ea 100644 --- a/assets/pl/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/pl/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py similarity index 96% rename from assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py rename to assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py index 9b3114e6..2687affd 100644 --- a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_BLOOMZ_ZeroShot.py +++ b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_BLOOMZ_ZeroShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py similarity index 97% rename from assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py rename to assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py index d4abcaac..5b6551b8 100644 --- a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_FewShot.py +++ b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_FewShot.py @@ -1,18 +1,18 @@ import os import re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py similarity index 97% rename from assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py rename to assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py index e2557173..9633b020 100644 --- a/assets/ru/factuality_disinformation_harmful_content/propaganda/PropMultilabel_GPT4_ZeroShot.py +++ b/assets/ru/factuality_disinformation_harmful_content/propaganda/SemEval23T3Propaganda_GPT4_ZeroShot.py @@ -2,18 +2,18 @@ import regex as re -from llmebench.datasets import PropagandaSemEval23Dataset +from llmebench.datasets import SemEval23T3PropagandaDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import PropagandaMultilabelSemEval23Task +from llmebench.tasks import SemEval23T3PropagandaTask def config(): return { - "dataset": PropagandaSemEval23Dataset, + "dataset": SemEval23T3PropagandaDataset, "dataset_args": { "techniques_path": "data/factuality_disinformation_harmful_content/propaganda_semeval23/techniques_subtask3.txt" }, - "task": PropagandaMultilabelSemEval23Task, + "task": SemEval23T3PropagandaTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py similarity index 91% rename from assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py rename to assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py index 61338f04..a3c08771 100644 --- a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_BLOOMZ_ZeroShot.py +++ b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_BLOOMZ_ZeroShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py similarity index 96% rename from assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py rename to assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py index c1ae1b57..c940592f 100644 --- a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_FewShot.py +++ b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_FewShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py similarity index 95% rename from assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py rename to assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py index 14ebc259..5041a952 100644 --- a/assets/tr/factuality_disinformation_harmful_content/checkworthyness/Checkworthiness_GPT4_ZeroShot.py +++ b/assets/tr/factuality_disinformation_harmful_content/checkworthyness/CT22Checkworthiness_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import CheckworthinessDataset +from llmebench.datasets import CT22CheckworthinessDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import CheckworthinessTask def config(): return { - "dataset": CheckworthinessDataset, + "dataset": CT22CheckworthinessDataset, "dataset_args": {}, "task": CheckworthinessTask, "task_args": {}, diff --git a/llmebench/datasets/FactualityCOVID19.py b/llmebench/datasets/COVID19Factuality.py similarity index 100% rename from llmebench/datasets/FactualityCOVID19.py rename to llmebench/datasets/COVID19Factuality.py diff --git a/llmebench/datasets/Attentionworthy.py b/llmebench/datasets/CT22Attentionworthy.py similarity index 96% rename from llmebench/datasets/Attentionworthy.py rename to llmebench/datasets/CT22Attentionworthy.py index f8978a5b..90123c31 100644 --- a/llmebench/datasets/Attentionworthy.py +++ b/llmebench/datasets/CT22Attentionworthy.py @@ -12,7 +12,7 @@ def get_data_sample(self): def metadata(): return { - "language": "ar", + "language": ["ar", "bg", "nl", "en", "tr"], "citation": """@InProceedings{clef-checkthat:2022:task1, author = {Nakov, Preslav and Barr\\'{o}n-Cede\\~{n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and M\\'{\\i}guez, Rub\'{e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and Li, Chengkai and Shaar, Shaden and Mubarak, Hamdy and Nikolov, Alex and Kartal, Yavuz Selim and Beltr\\'{a}n, Javier}, title = "Overview of the {CLEF}-2022 {CheckThat}! Lab Task 1 on Identifying Relevant Claims in Tweets", diff --git a/llmebench/datasets/Checkworthiness.py b/llmebench/datasets/CT22Checkworthiness.py similarity index 97% rename from llmebench/datasets/Checkworthiness.py rename to llmebench/datasets/CT22Checkworthiness.py index 9556d768..d257b219 100644 --- a/llmebench/datasets/Checkworthiness.py +++ b/llmebench/datasets/CT22Checkworthiness.py @@ -17,7 +17,7 @@ def get_data_sample(self): def metadata(): return { - "language": "ar", + "language": ["ar", "bg", "nl", "en", "tr"], "citation": """@inproceedings{nakov2022overview, title={Overview of the clef--2022 checkthat! lab on fighting the covid-19 infodemic and fake news detection}, author={Nakov, Preslav and Barr{\\'o}n-Cede{\\~n}o, Alberto and da San Martino, Giovanni and Alam, Firoj and Stru{\\ss}, Julia Maria and Mandl, Thomas and M{\\'\\i}guez, Rub{\\'e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and others}, diff --git a/llmebench/datasets/Claim.py b/llmebench/datasets/CT22Claim.py similarity index 90% rename from llmebench/datasets/Claim.py rename to llmebench/datasets/CT22Claim.py index 923ad528..83e8faf2 100644 --- a/llmebench/datasets/Claim.py +++ b/llmebench/datasets/CT22Claim.py @@ -1,15 +1,13 @@ -import pandas as pd - from llmebench.datasets.dataset_base import DatasetBase -class CovidClaimDataset(DatasetBase): +class CT22ClaimDataset(DatasetBase): def __init__(self, **kwargs): - super(CovidClaimDataset, self).__init__(**kwargs) + super(CT22ClaimDataset, self).__init__(**kwargs) def metadata(): return { - "language": "ar", + "language": ["ar", "bg", "nl", "en", "tr"], "citation": """@inproceedings{nakov2022overview, title={Overview of the CLEF-2022 CheckThat! lab task 1 on identifying relevant claims in tweets}, author={Nakov, Preslav and Barr{\\o}n-Cede{\\~n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and Kutlu, Mucahid and Zaghouani, Wajdi and Li, Chengkai and Shaar, Shaden and Mubarak, Hamdy and Nikolov, Alex}, diff --git a/llmebench/datasets/Harmful.py b/llmebench/datasets/CT22Harmful.py similarity index 100% rename from llmebench/datasets/Harmful.py rename to llmebench/datasets/CT22Harmful.py diff --git a/llmebench/datasets/Subjectivity.py b/llmebench/datasets/CT23Subjectivity.py similarity index 100% rename from llmebench/datasets/Subjectivity.py rename to llmebench/datasets/CT23Subjectivity.py diff --git a/llmebench/datasets/PropagandaSemEval23.py b/llmebench/datasets/SemEval23T3Propaganda.py similarity index 95% rename from llmebench/datasets/PropagandaSemEval23.py rename to llmebench/datasets/SemEval23T3Propaganda.py index cc130442..b0e13173 100644 --- a/llmebench/datasets/PropagandaSemEval23.py +++ b/llmebench/datasets/SemEval23T3Propaganda.py @@ -1,19 +1,18 @@ import json -import os from pathlib import Path from llmebench.datasets.dataset_base import DatasetBase -class PropagandaSemEval23Dataset(DatasetBase): +class SemEval23T3Dataset(DatasetBase): def __init__(self, techniques_path=None, **kwargs): # Get the path to the file listing the target techniques self.techniques_path = Path(techniques_path) if techniques_path else None - super(PropagandaSemEval23Dataset, self).__init__(**kwargs) + super(SemEval23T3Dataset, self).__init__(**kwargs) def metadata(): return { - "language": "multilingual", + "language": ["en", "es", "fr", "ge", "gr", "it", "ka", "po", "ru"], "citation": """@inproceedings{piskorski-etal-2023-semeval, title = "{S}em{E}val-2023 Task 3: Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup", author = "Piskorski, Jakub and diff --git a/llmebench/datasets/Propaganda.py b/llmebench/datasets/WANLP22T3Propaganda.py similarity index 76% rename from llmebench/datasets/Propaganda.py rename to llmebench/datasets/WANLP22T3Propaganda.py index e3e7074f..fc623ca8 100644 --- a/llmebench/datasets/Propaganda.py +++ b/llmebench/datasets/WANLP22T3Propaganda.py @@ -5,17 +5,22 @@ from llmebench.datasets.dataset_base import DatasetBase -class PropagandaTweetDataset(DatasetBase): +class WANLP22T3PropagandaDataset(DatasetBase): def __init__(self, techniques_path=None, **kwargs): # Get the path to the file listing the target techniques self.techniques_path = Path(techniques_path) if techniques_path else None - super(PropagandaTweetDataset, self).__init__(**kwargs) + super(WANLP22T3PropagandaDataset, self).__init__(**kwargs) def metadata(): return { "language": "ar", - "citation": """@article{wanlp2023, - year={2023} + "citation": """@inproceedings{alam2022overview, + title={Overview of the $\{$WANLP$\}$ 2022 Shared Task on Propaganda Detection in $\{$A$\}$ rabic}, + author={Alam, Firoj and Mubarak, Hamdy and Zaghouani, Wajdi and Da San Martino, Giovanni and Nakov, Preslav and others}, + booktitle={Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)}, + pages={108--118}, + year={2022}, + organization={Association for Computational Linguistics} }""", } diff --git a/llmebench/tasks/PropagandaMultilabelSemEval23.py b/llmebench/tasks/MultilabelPropaganda.py similarity index 86% rename from llmebench/tasks/PropagandaMultilabelSemEval23.py rename to llmebench/tasks/MultilabelPropaganda.py index 5e9b6dcd..e0a33eed 100644 --- a/llmebench/tasks/PropagandaMultilabelSemEval23.py +++ b/llmebench/tasks/MultilabelPropaganda.py @@ -1,14 +1,12 @@ -import itertools - from sklearn import preprocessing from sklearn.metrics import f1_score from llmebench.tasks.task_base import TaskBase -class PropagandaMultilabelSemEval23Task(TaskBase): +class SemEval23T3PropagandaTask(TaskBase): def __init__(self, **kwargs): - super(PropagandaMultilabelSemEval23Task, self).__init__(**kwargs) + super(SemEval23T3PropagandaTask, self).__init__(**kwargs) def evaluate(self, true_labels, predicted_labels): # Handle cases when model fails! diff --git a/llmebench/tasks/PropagandaMultilabel.py b/llmebench/tasks/PropagandaMultilabel.py deleted file mode 100644 index c661a2a1..00000000 --- a/llmebench/tasks/PropagandaMultilabel.py +++ /dev/null @@ -1,29 +0,0 @@ -import itertools - -from sklearn import preprocessing -from sklearn.metrics import f1_score - -from llmebench.tasks.task_base import TaskBase - - -class PropagandaMultilabelTask(TaskBase): - def __init__(self, **kwargs): - super(PropagandaMultilabelTask, self).__init__(**kwargs) - - def evaluate(self, true_labels, predicted_labels): - # Handle cases when model fails! - # Flatten true labels as it is a list of lists - predicted_labels = [p if p else ["no technique"] for p in predicted_labels] - - # Need the pre-defined list of techniques - techniques = self.dataset.get_predefined_techniques() - - # Binarize labels and use them for multi-label evaluation - mlb = preprocessing.MultiLabelBinarizer() - mlb.fit([techniques]) - gold = mlb.transform(true_labels) - pred = mlb.transform(predicted_labels) - - micro_f1 = f1_score(gold, pred, average="micro") - - return {"Micro F1": micro_f1} diff --git a/llmebench/tasks/Subjectivity.py b/llmebench/tasks/Subjectivity.py index 96272969..e88e3e63 100644 --- a/llmebench/tasks/Subjectivity.py +++ b/llmebench/tasks/Subjectivity.py @@ -9,9 +9,9 @@ from llmebench.tasks.task_base import TaskBase -class SubjectivityTask(TaskBase): +class CT23SubjectivityTask(TaskBase): def __init__(self, **kwargs): - super(SubjectivityTask, self).__init__(**kwargs) + super(CT23SubjectivityTask, self).__init__(**kwargs) def evaluate(self, gold_labels, pred_labels): pred_labels = [