作者位次 #5/9ACL 2026Findings· Findings of ACL
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
Aakriti Agrawal · Gouthaman KV · Rohith Aralikatti · Gauri Jagatap · Jiaxin Yuan · Sarvesh Baskar · Vijay Kamarshi · Andrea Fanelli · Furong Huang
摘要
Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning. A key cause is the model’s over-reliance on textual priors and underutilization of visual cues, leading to outputs th...