VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
VisER is proposed, a training-free two-sided metric for object-level hallucination detection that improves AUROC and AUPR over a range of baselines and measures whether object-context compatibility is backed by object-specific evidence from image tokens.
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.
· 0 citations