rm_vs_dm

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting

This directory contains source code accompanying the paper On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting (NeurIPS 2022).

Contributors

Tomasz Korbak, [email protected]

Hady Elsahar, [email protected]

Germán Kruszewski, [email protected]

Marc Dymetman, [email protected]

Citation

@inproceedings{
korbak2022on,
title={On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting},
author={Tomasz Korbak and Hady Elsahar and Germ{\'a}n Kruszewski and Marc Dymetman},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=XvI6h-s4un}
}