Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
arXiv preprint arXiv:2501.16629 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
PSRD mitigates visual hallucinations in LVLMs via phase-wise self-reward decoding, cutting rates by 50% on LLaVA-1.5-7B and outperforming prior methods on five benchmarks.
MPD reduces hallucinations in LVLMs by 23.4% while retaining 97.4% of general capability through semantic disentanglement and selective parameter updates.
citing papers explorer
No citing papers match the current filters.