MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization
MoD-DPO:通过模态解耦偏好优化缓解多模态幻觉
机构 * University of Southern California(南加州大学)
专题命中 偏好对齐 :DPO(title,abstract);alignment(abstract);分类 cs.CL、cs.LG
AI总结 本文提出MoD-DPO框架,通过引入模态感知正则化项和语言先验去偏惩罚,提升多模态大模型的模态对齐能力,实验表明其在多模态幻觉基准测试中表现优异。
Comments CVPR 2026. Project Page: https://mod-dpo.github.io/