# MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context

arXiv: https://arxiv.org/abs/2407.02730 · HTML: https://mlsanity.com/paper/2407.02730/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 11 of 11)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation](https://mlsanity.com/paper/2401.12208/) (2024)
- [LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation](https://mlsanity.com/paper/2305.11490/) (2023)
- [CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain](https://mlsanity.com/paper/2212.02974/) (2022)
- [How well do LLMs cite relevant medical references? An evaluation framework and analyses](https://mlsanity.com/paper/2402.02008/) (2024)
- [Hardware Phi-1.5B: A Large Language Model Encodes Hardware Domain Specific Knowledge](https://mlsanity.com/paper/2402.01728/) (2024)

## Built on by (most cited first, 20 of 20)

- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models](https://mlsanity.com/paper/2502.20780/) (2025)
- [Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2512.01922/) (2025)
- [CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding](https://mlsanity.com/paper/2509.23379/) (2025)
- [Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives](https://mlsanity.com/paper/2502.16841/) (2025)
- [Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability](https://mlsanity.com/paper/2504.21625/) (2025)
- [Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning](https://mlsanity.com/paper/2505.18503/) (2025)
- [A Scoping Review of Natural Language Processing in Addressing Medically Inaccurate Information: Errors, Misinformation, and Hallucination](https://mlsanity.com/paper/2505.00008/) (2025)
- [EH-Benchmark Ophthalmic Hallucination Benchmark and Agent-Driven Top-Down Traceable Reasoning Workflow](https://mlsanity.com/paper/2507.22929/) (2025)
- [MedErr-CT: A Visual Question Answering Benchmark for Identifying and Correcting Errors in CT Reports](https://mlsanity.com/paper/2506.19217/) (2025)
- [MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing](https://mlsanity.com/paper/2508.01653/) (2025)
- [Enhancing Medical Large Vision-Language Models via Alignment Distillation](https://mlsanity.com/paper/2512.18554/) (2025)
- [Attention Without Grounding: Causal Evaluation of Visual Explanations in Medical VLMs](https://mlsanity.com/paper/2607.18577/) (2026)
- [Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam](https://mlsanity.com/paper/2507.19885/) (2025)
- [NEURO-GUARD: Neuro-Symbolic Generalization and Unbiased Adaptive Routing for Diagnostics -- Explainable Medical AI](https://mlsanity.com/paper/2512.18177/) (2025)
- [Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework](https://mlsanity.com/paper/2604.18145/) (2026)
- [MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence](https://mlsanity.com/paper/2605.07919/) (2026)
- [HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation](https://mlsanity.com/paper/2605.20469/) (2026)
- [Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA](https://mlsanity.com/paper/2609.00959/) (2026)
- [A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care](https://mlsanity.com/paper/2610.07339/) (2026)

## Abstract (arXiv)

Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical context, which includes tasks for comprehensive understanding of textual and visual input, as well as long textual response generation. Our extensive experiments with both general and medical LVLMs reveal that, although medical LVLMs demonstrate promising performance on standard medical tasks, they are particularly susceptible to hallucinations, often more so than the general models, raising significant concerns about the reliability of these domain-specific models. For medical LVLMs to be truly valuable in real-world applications, they must not only accurately integrate medical knowledge but also maintain robust reasoning abilities to prevent hallucination. Our work paves the way for future evaluations of these studies.