Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation 事件

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation arXiv:2605.25377v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external interventions, such as instruction tuning and retrieval, or use internal mechanisms that remain limited by flawed attention weights and en