@inproceedings{wang-etal-2024-mdpo,
    title = "m{DPO}: Conditional Preference Optimization for Multimodal Large Language Models",
    author = "Wang, Fei  and
      Zhou, Wenxuan  and
      Huang, James Y.  and
      Xu, Nan  and
      Zhang, Sheng  and
      Poon, Hoifung  and
      Chen, Muhao",
    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/jlcl-multiple-ingestion/2024.emnlp-main.460/",
    doi = "10.18653/v1/2024.emnlp-main.460",
    pages = "8078--8088",
    abstract = "Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we introduce a reward anchor that forces the reward to be positive for chosen responses, thereby avoiding the decrease in their likelihood{---}an intrinsic problem of relative preference optimization. Experiments on two multimodal LLMs of different sizes and three widely used benchmarks demonstrate that mDPO effectively addresses the unconditional preference problem in multimodal preference optimization and significantly improves model performance, particularly in reducing hallucination."
}