VEPO2 min read
VEPO: Mitigating Multilingual Hallucinations in LVLMs via Visual Evidence-guided Preference Optimization
Large vision-language models (LVLMs) achieve strong multimodal performance, yet they remain prone to object hallucination---generating answers that are linguistically fluent but visually ungrounded.
By Chengpeng Fu, Xiaocheng Feng, Wenshuai Huo, Yichong Huang, Baohang Li, Duyu Tang, Ting LiuarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 16, 2026.
Comments
Sign in to join the discussion.