VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but lack visual grounding. Recent training-free detectors use internal signals such as token likelihood, attention, visual confidence, or image-text similarity to identify hallucinated objects. These signals are useful, but they are often source-confounded. They measure how strongly an object is supported inside the model without distinguishing whether that support comes from object-specific visual evidence or the generated text prefix. In difficult c
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Models Produce Hallucinations Because of Probabilistic Training - Let's Data Science →
- PossiblePossibly related (embedding) · 53%Hallucination →
- LinkedLinked via arxiv author · 85%Afsaneh Hasanebrahimi →
“VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs”
- LinkedLinked via arxiv author · 85%Hanxun Huang →
“VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs”
- LinkedLinked via arxiv author · 85%Christopher Leckie →
“VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs”
- LinkedLinked via arxiv author · 85%Sarah Erfani →
“VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs”
- PossiblePossibly related (embedding) · 60%Researchers develop cost-efficient method for detecting hallucinations in large language models - Tech Xplore →