# GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2506.17939 · HTML: https://mlsanity.com/paper/2506.17939/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning](https://mlsanity.com/paper/2505.08617/) (2025)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning](https://mlsanity.com/paper/2402.06332/) (2024)
- [Preference Optimization for Reasoning with Pseudo Feedback](https://mlsanity.com/paper/2411.16345/) (2024)
- [CodeDPO: Aligning Code Models with Self Generated and Verified Source Code](https://mlsanity.com/paper/2410.05605/) (2024)
- [Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning](https://mlsanity.com/paper/2506.10521/) (2025)
- [GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis](https://mlsanity.com/paper/2411.16778/) (2024)
- [MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs](https://mlsanity.com/paper/2505.20740/) (2025)
- [Group Relative Policy Optimization for Image Captioning](https://mlsanity.com/paper/2503.01333/) (2025)
- [EyeGPT: Ophthalmic Assistant with Large Language Models](https://mlsanity.com/paper/2403.00840/) (2024)

## Built on by (most cited first, 8 of 8)

- [Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications](https://mlsanity.com/paper/2508.00669/) (2025)
- [OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning](https://mlsanity.com/paper/2511.23269/) (2025)
- [MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.08203/) (2026)
- [Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation](https://mlsanity.com/paper/2508.12957/) (2025)
- [Towards Clinically Interpretable Ophthalmic VQA via Spatially-Grounded Lesion Evidence](https://mlsanity.com/paper/2605.22414/) (2026)
- [CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs](https://mlsanity.com/paper/2606.27264/) (2026)
- [UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound](https://mlsanity.com/paper/2609.30928/) (2026)
- [Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients](https://mlsanity.com/paper/2512.23090/) (2025)

## Abstract (arXiv)

Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images. While recent advances in multi-modal learning have significantly improved performance, current methods still suffer from limited answer reliability and poor interpretability, impairing the ability of clinicians and patients to understand and trust model outputs. To address these limitations, this work first proposes a Region-Aware Multimodal Chain-of-Thought (RMCoT) dataset, in which the process of producing an answer is preceded by a sequence of intermediate reasoning steps that explicitly ground relevant visual regions of the medical image, thereby providing fine-grained explainability. Furthermore, we introduce a novel verifiable reward mechanism for reinforcement learning to guide post-training, improving the alignment between the model's reasoning process and its final answer. Remarkably, our method achieves comparable performance using only one-eighth of the training data, demonstrating the efficiency and effectiveness of the proposal. The dataset is available at https://www.med-vqa.com/GEMeX/.