AI RESEARCH
Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework
arXiv CS.CV
•
ArXi:2601.22451v2 Announce Type: replace Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work attributes this to LVLMs' over-reliance on language priors and attempts to mitigate it through logits calibration. However, they still lack a thorough analysis of the over-reliance.