ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback

ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback Ju-Seung Byun author Jiyun Chun author Jihyung Kil author Andrew Perrault author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication byun-etal-2024-ares 10.18653/v1/2024.emnlp-main.252 https://aclanthology.org/2024.emnlp-main.252/ 2024-11 4410 4430