Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating

• URL: http://arxiv.org/abs/2605.24024v1
• Date: Wed, 20 May 2026 13:29:29 GMT
• Title: Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating
• Abstract summary: Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image.<n>We show that a key failure mode arises from route competition, causing the decoder to follow linguistic priors over visual evidence.<n>We propose a training-free, decision-aligned intervention that decomposes each attention head into a visual route and a text route.
• Score: 4.514623850633406
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual tokens receive attention, the final token decision can be dominated by the textual pathway, causing the decoder to follow linguistic priors over visual evidence. To mitigate this, we propose a training-free, decision-aligned intervention that decomposes each attention head into a visual route and a text route, and estimates their token-level effects using an efficient one-forward/one-gradient approximation. These estimates reveal route conflict within heads and identify prior-dominant ones, enabling selective suppression of only the text route while keeping the visual route intact. Across five benchmarks spanning discriminative and generative settings, our method consistently reduces hallucination-related errors across models with limited impact on overall multimodal performance, while incurring a modest inference-time overhead.

Related papers

• Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation [59.80828456543202]
  We propose Token-Level Visual-Sensitivity Steering (TLVS) for hallucination mitigation.<n>This mechanism requires only minimal training for calibration and can be applied across diverse vision-language models.<n>We evaluate TLVS on several benchmarks, including POPE, AMBER, CHAIR (COCO), MMHal, and HallusionBench, demonstrating consistent improvements over previous steering methods.
  arXiv  Detail & Related papers  (2026-06-02T08:23:28Z)
• Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration [7.647944993041615]
  We introduce a training-free inference strategy to dynamically correct semantic drift without relying on abrupt truncations.<n>By computing an outlier-resistant statistical midpoint across various attention heads, we establish a stable anchor for reliable visual representations.<n>This recalibration process effectively rectifies visual-semantic misalignments while fully preserving generative fluency and language priors.
  arXiv  Detail & Related papers  (2026-05-24T09:14:49Z)
• CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs [16.77211535169488]
  We propose Contrastive Hallucination-Aware Step-wise Decoding (CHASD) for Large Vision-Language Models.<n> CHASD uses an uncertainty-driven confidence gate to activate the contrastive branch only when the maximum probability of the next-token is less than the threshold.<n> Experiments show that CHASD improves hallucination-related metrics over strong training-free baselines with competitive inference efficiency.
  arXiv  Detail & Related papers  (2026-05-22T08:03:12Z)
• Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction [49.96701537295129]
  Large Vision-Language Models (LVLMs) have achieved remarkable success across cross-modal tasks but remain hindered by hallucinations.<n>Existing methods mitigate hallucinations but often alter generation behavior, resulting in shorter outputs and shifted token distributions.<n>We propose MESA, an effective plug-and-play framework that performs controlled and selective latent intervention for hallucination mitigation.
  arXiv  Detail & Related papers  (2026-04-09T07:31:27Z)
• Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Models [8.304027910542446]
  We investigate the internal attention dynamics of vision encoders in Large Vision-Language Models (LVLMs)<n>Our analysis reveals that hallucination behavior is particularly sensitive to tokens receiving low attention during the focus phase.<n>We propose a lightweight inference-time intervention that selectively suppresses such tokens during the focus phase.
  arXiv  Detail & Related papers  (2026-04-04T02:46:58Z)
• ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration [71.21097024566285]
  Large-Language Models (LVLMs) frequently suffer from severe hallucination issues.<n>Existing mitigation strategies rely on linguistic, single-step states to enhance visual focus or suppress strong priors.<n>We propose Adaptive Context in VisionTegration (ACT), a training-free inference intervention method that mitigates hallucination through the adaptive integration of contextual information.
  arXiv  Detail & Related papers  (2026-04-01T14:49:50Z)
• Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs [9.043999205886658]
  Hallucinations in large vision-language models often arise when language priors dominate over visual evidence.<n>We propose Contrastive Guidance (ACG), a single-pass mechanism that operates within self-attention layers to construct both vision-language and language-only attention paths.<n>ACG achieves state-of-the-art faithfulness and caption quality while significantly reducing computational cost.
  arXiv  Detail & Related papers  (2026-01-20T08:04:18Z)
• Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs [51.93737995405164]
  Large Vision-Language Models (LVLMs) are susceptible to hallucinations.<n>We introduce a novel Conditional Pointwise Mutual Information (C-PMI) calibrated decoding strategy.<n>We show that the proposed method significantly reduces hallucinations in LVLMs while preserving decoding efficiency.
  arXiv  Detail & Related papers  (2025-05-26T08:36:10Z)
• PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training [56.172959986096316]
  This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs)<n>HalFscore is a novel metric built upon the language graph and is designed to evaluate both the accuracy and completeness of dense captions at a granular level.<n>PerturboLLaVA significantly improves the fidelity of generated captions, outperforming existing approaches in handling multimodal hallucinations.
  arXiv  Detail & Related papers  (2025-03-09T07:07:03Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding [25.489832294197797]
  This paper introduces the Instruction Contrastive Decoding (ICD) method, a novel approach designed to reduce hallucinations during LVLM inference. Our method is inspired by our observation that what we call disturbance instructions significantly exacerbate hallucinations in multimodal fusion modules.
  arXiv  Detail & Related papers  (2024-03-27T16:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.