mlsanityData to 7 Oct 2026

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models

arXiv 2502.20780 ↗First posted 28 Feb 2025cs.AI cs.CL cs.CVcited by 6

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

Abstract (arXiv)

The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may generate seemingly plausible results that are in fact incorrect. Such hallucinations can jeopardize clinical decision making, potentially harming the diagnosis and treatments. In this work, we propose MedHallTune, a large-scale benchmark designed specifically to evaluate and mitigate hallucinations in medical VLMs. Comprising over 100,000 images and 1,000,000 instruction pairs, MedHallTune includes both hallucination and non-hallucination samples, each with ground-truth annotations. We conduct a comprehensive evaluation of current medical and general VLMs using MedHallTune, assessing their performance across key metrics, including clinical accuracy, relevance, detail level, and risk level. The experimental results show that fine-tuning with MedHallTune successfully improves the ability of several existing models to manage hallucinations and boost their zero-shot performance on downstream visual-question-answering (VQA) tasks, making them more reliable for practical medical applications. Our work contributes to the development of more trustworthy VLMs. Codes and dataset will be available at hrefhttps://github.com/russellyq/MedHallTuneMedHallTune.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 40 of its 62 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

40 of 62 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Mitigating Object Hallucination via Concentric Causal Attention21 Oct
  2. 2024MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context3 Jul
  3. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Models14 Jun
  4. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  5. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models23 Oct
  6. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun

Other references · 34

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  6. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  9. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  10. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  11. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  12. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
22 more
  1. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  2. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
  3. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
  4. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 444
  5. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  6. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 333
  7. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  8. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 201
  9. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 182
  10. 2023Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Datacited by 176
  11. 2023Med-HALT: Medical Domain Hallucination Test for Large Language Modelscited by 156
  12. 2023A Survey of Large Language Models in Medicine: Progress, Application, and Challengecited by 123
  13. 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptationcited by 112
  14. 2024A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretationcited by 79
  15. 2024MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicinecited by 79
  16. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 72
  17. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 64
  18. 2024GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaborationcited by 33
  19. 2024STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answeringcited by 21
  20. 2024MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Modelscited by 20
  21. 2024BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalitiescited by 20
  22. 2024PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understandingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  2. 2025UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Modelscited by 5
  3. 2026Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steeringcited by 1
  4. 2026ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoningcited by 1
  5. 2026Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Modelscited by 0
  6. 2026SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models
  2. 2024MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models
  3. 2026Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
  4. 2025Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding
  5. 2025Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
  6. 2026VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
  7. 2026Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
  8. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models