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.

通过比较性实验，我们识别出多模态偏好优化中的无条件偏好问题，并提出 mDPO，一种多模态 DPO 目标，通过优化图像偏好来避免只优化语言偏好。同时引入一种奖励锚点，强制奖励对于选择的回答是正面的，从而避免相对偏好优化的内在问题。在两种不同规模的多模态 LLM 和三个广泛使用的基准测试中进行的实验表明，mDPO 在处理多模态偏好优化的无条件偏好问题上是有效的，并在模型性能方面取得了显著改进，尤其是在减少幻觉方面。