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.
Mitigating object hallucinations in large vision-language models via attention calibration.arXiv preprint arXiv:2502.01969
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
DaID mitigates MLLM hallucinations by attention-guided selection of dual layers that calibrate token generation using internal perceptual discrepancies.
SinkTrack anchors LLMs to initial context by modifying the attention sink token with injected features, yielding gains on textual and multimodal tasks.
CAAC mitigates hallucinations in LVLMs via Visual-Token Calibration and Adaptive Attention Re-Scaling guided by model confidence, showing gains on CHAIR, AMBER, and POPE especially in long-form generation.
citing papers explorer
-
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.
-
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
DaID mitigates MLLM hallucinations by attention-guided selection of dual layers that calibrate token generation using internal perceptual discrepancies.
-
SinkTrack: Attention Sink based Context Anchoring for Large Language Models
SinkTrack anchors LLMs to initial context by modifying the attention sink token with injected features, yielding gains on textual and multimodal tasks.
-
Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
CAAC mitigates hallucinations in LVLMs via Visual-Token Calibration and Adaptive Attention Re-Scaling guided by model confidence, showing gains on CHAIR, AMBER, and POPE especially in long-form generation.