mlsanityData to 7 Oct 2026

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning

arXiv 2408.17150 ↗First posted 30 Aug 2024cs.CV cs.AIcited by 23

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

Recently, Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multi-modal context comprehension. However, they still suffer from hallucination problems referring to generating inconsistent outputs with the image content. To mitigate hallucinations, previous studies mainly focus on retraining LVLMs with custom datasets. Although effective, they inherently come with additional computational costs. In this paper, we propose a training-free framework, MVP, that aims to reduce hallucinations by making the most of the innate capabilities of the LVLMs via Multi-View Multi-Path Reasoning. Specifically, we first devise a multi-view information-seeking strategy to thoroughly perceive the comprehensive information in the image, which enriches the general global information captured by the original vision encoder in LVLMs. Furthermore, during the answer decoding, we observe that the occurrence of hallucinations has a strong correlation with the certainty of the answer tokens. Thus, we propose multi-path reasoning for each information view to quantify and aggregate the certainty scores for each potential answer among multiple decoding paths and finally decide the output answer. By fully grasping the information in the image and carefully considering the certainty of the potential answers when decoding, our MVP can effectively reduce hallucinations in LVLMs.The extensive experiments verify that our proposed MVP significantly mitigates the hallucination problem across four well-known LVLMs. The source code is available at: urlhttps://github.com/GasolSun36/MVP.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 23 of its 39 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

23 of 39 references.

References · 23

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  3. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  4. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  5. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
  6. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  7. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 468
  8. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 404
  9. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 223
  10. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 223
  11. 2024Twin-Merging: Dynamic Integration of Modular Expertise in Model Mergingcited by 114
  12. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 82
11 more
  1. 2024ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMcited by 73
  2. 2023Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcarecited by 62
  3. 2023Mitigating Hallucination in Visual Language Models with Visual Supervisioncited by 49
  4. 2024Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidancecited by 44
  5. 2024ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modelingcited by 34
  6. 2024Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentationcited by 27
  7. 2024VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Frameworkcited by 20
  8. 2024Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learningcited by 9
  9. 2024Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuningcited by 7
  10. 2024Mitigating Multilingual Hallucination in Large Vision-Language Modelscited by 3
  11. 2024Online Robot Navigation and Manipulation with Distilled Vision-Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 12; 2026: 6.

23 papers.

Sort:

By area:

  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  2. 2024Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Modelscited by 72
  3. 2025Grounded Chain-of-Thought for Multimodal Large Language Modelscited by 57
  4. 2024Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Modelscited by 41
  5. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  6. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)cited by 23
  7. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  8. 2024Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Networkcited by 15
  9. 2025LanP: Rethinking the Impact of Language Priors in Large Vision-Language Modelscited by 14
  10. 2024SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Informationcited by 11
  11. 2025Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decodingcited by 10
  12. 2025INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Samplingcited by 10
11 more
  1. 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibrationcited by 8
  2. 2025A Multimodal Multi-Agent Framework for Radiology Report Generationcited by 8
  3. 2025OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucinationcited by 8
  4. 2025A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answeringcited by 1
  5. 2026Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platformcited by 1
  6. 2026RSHallu: Dual-Mode Hallucination Evaluation for Remote-Sensing Multimodal Large Language Models with Domain-Tailored Mitigationcited by 1
  7. 2025Conscious Gaze: Adaptive Attention Mechanisms for Hallucination Mitigation in Vision-Language Modelscited by 0
  8. 2026Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learningcited by 0
  9. 2026VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editingcited by 0
  10. 2026Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Modelscited by 0
  11. 2026DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
  2. 2025ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
  3. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  4. 2026Revealing Multi-View Hallucination in Large Vision-Language Models
  5. 2026Hallucination-aware intermediate representation edit in large vision-language models
  6. 2025VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
  7. 2025Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
  8. 2024VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding