@inproceedings{byun-etal-2024-ares,
    title = "{ARES}: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse {AI} Feedback",
    author = "Byun, Ju-Seung  and
      Chun, Jiyun  and
      Kil, Jihyung  and
      Perrault, Andrew",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.252/",
    doi = "10.18653/v1/2024.emnlp-main.252",
    pages = "4410--4430"
}