gagaein

Hello, I am facing the same problem. Have you solved it:)

Thank you for your reply! I see the annotation trouble of Twitter-2015. That's really strange :( I will try to use your evaluation script to get the right performance scores....

> 感谢关注！我们建议的复现论文中性能最好的方法就是按照论文中的 iterative 方式进行数据构造和训练。我们近期会开源使用 RLAIF-V 作为 reward model 直接构造高质量数据的方法，并且在定量实验中发现这样构造的数据效率也较高并且在单轮训练中就能取得不错的效果，希望能够帮助到您！ > > Thank you for your interest! We recommend reproducing the best-performing method in the paper by following the iterative approach...