 Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning TasksAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Justice or Prejudice? Quantifying Biases in LLM-as-a-JudgeInternational Conference on Learning Representations (ICLR), 2024 Jiayi Ye Zixiang Xu Yue Huang Dongping Chen Qihui Zhang ...Werner Geyer Chao Huang Pin-Yu Chen Nitesh Chawla Xiangliang Zhang |
 Feedback Loops With Language Models Drive In-Context Reward HackingInternational Conference on Machine Learning (ICML), 2024 |
