# EH-Benchmark Ophthalmic Hallucination Benchmark and Agent-Driven Top-Down Traceable Reasoning Workflow

arXiv: https://arxiv.org/abs/2507.22929 · HTML: https://mlsanity.com/paper/2507.22929/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 29 of its 69 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation](https://mlsanity.com/paper/2502.09838/) (2025)
- [Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance](https://mlsanity.com/paper/2410.16261/) (2024)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [Detecting and Evaluating Medical Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2406.10185/) (2024)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models](https://mlsanity.com/paper/2310.08975/) (2023)
- [LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation](https://mlsanity.com/paper/2506.04078/) (2025)
- [EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model](https://mlsanity.com/paper/2504.13650/) (2025)
- [MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context](https://mlsanity.com/paper/2407.02730/) (2024)
- [MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM](https://mlsanity.com/paper/2409.00924/) (2024)
- [MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models](https://mlsanity.com/paper/2412.18947/) (2024)
- [Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2501.18119/) (2025)
- [MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models](https://mlsanity.com/paper/2503.02157/) (2025)
- [Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models](https://mlsanity.com/paper/2406.17115/) (2024)
- [LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2410.01620/) (2024)
- [FunBench: Benchmarking Fundus Reading Skills of MLLMs](https://mlsanity.com/paper/2503.00901/) (2025)
- [An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care](https://mlsanity.com/paper/2505.08414/) (2025)

## Built on by (most cited first, 2 of 2)

- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy](https://mlsanity.com/paper/2607.11175/) (2026)

## Abstract (arXiv)

Medical Large Language Models (MLLMs) play a crucial role in ophthalmic diagnosis, holding significant potential to address vision-threatening diseases. However, their accuracy is constrained by hallucinations stemming from limited ophthalmic knowledge, insufficient visual localization and reasoning capabilities, and a scarcity of multimodal ophthalmic data, which collectively impede precise lesion detection and disease diagnosis. Furthermore, existing medical benchmarks fail to effectively evaluate various types of hallucinations or provide actionable solutions to mitigate them. To address the above challenges, we introduce EH-Benchmark, a novel ophthalmology benchmark designed to evaluate hallucinations in MLLMs. We categorize MLLMs' hallucinations based on specific tasks and error types into two primary classes: Visual Understanding and Logical Composition, each comprising multiple subclasses. Given that MLLMs predominantly rely on language-based reasoning rather than visual processing, we propose an agent-centric, three-phase framework, including the Knowledge-Level Retrieval stage, the Task-Level Case Studies stage, and the Result-Level Validation stage. Experimental results show that our multi-agent framework significantly mitigates both types of hallucinations, enhancing accuracy, interpretability, and reliability. Our project is available at https://github.com/ppxy1/EH-Benchmark.