AOD isolates hallucination signals in LVLM representations with an adversarial minimax objective and uses dual-forward contrastive decoding to reduce hallucinations while preserving utility.
Attention hijackers: Detect and disentan- gle attention hijacking in lvlms for hallucination mitigation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
background 1representative citing papers
UE-DPO quantifies epistemic uncertainty from grounding failures to direct more learning pressure on hard visual tokens in preferred samples while easing penalties on dispreferred ones.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
citing papers explorer
-
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
AOD isolates hallucination signals in LVLM representations with an adversarial minimax objective and uses dual-forward contrastive decoding to reduce hallucinations while preserving utility.
-
Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
UE-DPO quantifies epistemic uncertainty from grounding failures to direct more learning pressure on hard visual tokens in preferred samples while easing penalties on dispreferred ones.