Data sampling of InternVL2.5-MPO

[manglu097]

“Regarding the phrase ‘For instructions with clear ground truths’ mentioned in Section 3.1 of the article, I would like to know how the author evaluates whether the generated responses match the ground truth?” Thanks

[yuecao0119]

Hello,

As stated in the original text, we force the model to output the final answer in the form of 'Final Answer: xxx' at the end. So for the final answer, we can match it with ground truth rules to determine if the answer is correct.

[manglu097]

“Thank you for your response! Do you mean exact matching? However, the model’s output ‘final answer’ might have the same meaning but in different forms, such as 0.3 and 3/10, or ‘yes’ and ‘yep’. In cases like this, how do you handle the matching? Is there a script in the repository for this? (I couldn’t find it.)”