mlsanityData to 14 Oct 2026

From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models

arXiv 2610.17706 ↗First posted 13 Oct 2026cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Large vision-language models often exhibit object hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-Guided Visual Claim Admission (EGVCA), a training-free framework that admits a semantic claim only when it receives sufficient image-dependent support. EGVCA measures this support by comparing the claim likelihood under the observed image and a visual-null input. For captioning, it controls semantic expansion without altering token generation. For binary visual question answering, it combines atomic visual support with the image-induced change in the model's native Yes--No margin. Experiments on CHAIR, POPE, and MME across three LVLM backbones show that EGVCA substantially reduces object hallucination while preserving caption quality. It achieves the highest POPE F1 in eight of nine backbone--sampling settings and improves the native MME total score on all three backbones. These results demonstrate the effectiveness of claim-level admission as a simple alternative to token-level distribution correction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 19 of its 29 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

19 of 29 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction30 Jul
  2. 2026AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing5 Jan
  3. 2026CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models2 Jan
  4. 2024Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding17 Oct
  5. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models4 Aug
  6. 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
  7. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding1 Mar
  8. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  9. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  10. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation13 Nov

Other references · 9

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  4. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  5. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  6. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 824
  7. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  8. 2026Mechanistic Circuit Identification for Controllable Data Generationcited by 2
  9. 2026The Hallucination Signal Is a Mean Shift: Why Simple Probes Sufficecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models
  2. 2023Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites
  3. 2025CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
  4. 2026ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models
  5. 2024Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
  6. 2024A Unified Hallucination Mitigation Framework for Large Vision-Language Models
  7. 2026Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
  8. 2023HallE-Control: Controlling Object Hallucination in Large Multimodal Models