proactive output任务分数计算问题

[wusj18]

hi，您好，
我在阅读您提供的官方代码过程中有一点疑问，想请教一下。
StreamingBench/src/data/count.py文件中，第38-55行的部分，您对proactive output任务的得分进行了统计，但我看到您只计算了模型回答问题的时间范围，并没有核对模型回答的答案内容。请问proactive output任务是只需要校验模型回答的时机，不需要校验模型回答的内容吗？
期待您的回复。

[mjuicem]

Hello! Thank you for your feedback.

We have addressed this concern and have updated the scoring logic in src/data/count.py. The current evaluation metric now takes into account both dimensions:

1. The timing of the model's response
2. The accuracy of the model's response content

You can find these changes in the latest version of the code. The updated implementation ensures a more comprehensive evaluation of the model's proactive output performance.

Let us know if you have any other questions!

Best regards