GEASS is a logit-level gating module that selectively trusts generated captions in VLMs per query by combining clean-path confidence, entropy reduction, and pathway disagreement, improving results on POPE and HallusionBench across four models.
The hidden life of tokens: Reducing hallucination of large vision-language models via visual information steering.arXiv preprint arXiv:2502.03628
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.
Decoder-based VLMs over-align visual embeddings to text manifold causing linguistic bias in top PCs of a universal text subspace; projecting out this subspace reduces hallucinations on POPE/CHAIR/AMBER and improves CLAIR.
RUDDER creates a persistent visual anchor by extracting CARD from prefill residuals and modulating its injection via an adaptive Beta Gate, cutting CHAIR_S by 24.4% and CHAIR_i by 23.6% on average across LLaVA, Idefics2, InstructBLIP and Qwen2.5-VL with >96% throughput.
FADE attenuates FFN outputs at critical layers in LVLMs to curb language-prior dominance and cut hallucinations, shown effective on POPE, CHAIR, and MME across three models.
MultiToP mitigates hallucinations in video multimodal models by training a Visual Token Patcher with information-guided rank calibration to selectively replace unreliable tokens, yielding 50.60% F1 gain on Vript-HAL and 18.58% accuracy gain on ActivityNet-QA.
ACE uses adversarial counter-commonsense perturbations on image tokens during decoding to suppress hallucinated linguistic priors while preserving stable visual signals in MLLMs.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
A training-free region-aware attention recalibration strategy reduces object hallucinations in LVLMs on CHAIR, POPE, and MME benchmarks while preserving fluency.
Steering is positioned as a distinct adaptation paradigm that uses targeted activation interventions for local, reversible behavioral changes without parameter updates.
citing papers explorer
-
GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models
GEASS is a logit-level gating module that selectively trusts generated captions in VLMs per query by combining clean-path confidence, entropy reduction, and pathway disagreement, improving results on POPE and HallusionBench across four models.
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
-
Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.
-
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
Decoder-based VLMs over-align visual embeddings to text manifold causing linguistic bias in top PCs of a universal text subspace; projecting out this subspace reduces hallucinations on POPE/CHAIR/AMBER and improves CLAIR.
-
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
FADE attenuates FFN outputs at critical layers in LVLMs to curb language-prior dominance and cut hallucinations, shown effective on POPE, CHAIR, and MME across three models.
-
MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models
MultiToP mitigates hallucinations in video multimodal models by training a Visual Token Patcher with information-guided rank calibration to selectively replace unreliable tokens, yielding 50.60% F1 gain on Vript-HAL and 18.58% accuracy gain on ActivityNet-QA.
-
Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
ACE uses adversarial counter-commonsense perturbations on image tokens during decoding to suppress hallucinated linguistic priors while preserving stable visual signals in MLLMs.
-
Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
A training-free region-aware attention recalibration strategy reduces object hallucinations in LVLMs on CHAIR, POPE, and MME benchmarks while preserving fluency.
-
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
Steering is positioned as a distinct adaptation paradigm that uses targeted activation interventions for local, reversible behavioral changes without parameter updates.