# EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning

arXiv: https://arxiv.org/abs/2510.19893 · HTML: https://mlsanity.com/paper/2510.19893/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2305.17100/) (2023)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context](https://mlsanity.com/paper/2008.07360/) (2020)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones](https://mlsanity.com/paper/2007.00478/) (2020)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Fairness in Reinforcement Learning](https://mlsanity.com/paper/1611.03071/) (2016)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation](https://mlsanity.com/paper/2106.12387/) (2021)
- [FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models](https://mlsanity.com/paper/2407.00983/) (2024)
- [QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training](https://mlsanity.com/paper/2506.00711/) (2025)
- [Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Review](https://mlsanity.com/paper/2203.15588/) (2022)
- [Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learning](https://mlsanity.com/paper/2201.00140/) (2022)
- [Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions](https://mlsanity.com/paper/2306.04597/) (2023)

## Abstract (arXiv)

Medical AI systems demonstrated impressive diagnostic performance, yet they routinely show uneven accuracy across demographic groups, disadvantaging underrepresented populations. Although multimodal reasoning foundation models have pushed clinical diagnosis forward, reinforcement learning-based post-training tends to absorb and magnify the biases present in majority-dominated training corpora. We propose Equitable Group Relative Policy Optimization (EQPO), a hierarchical reinforcement learning method that encourages balanced learning across heterogeneous clinical populations by adaptively reweighting samples according to subgroup representation, task difficulty, and data source. As demographic annotations are frequently missing in real-world clinical data, EQPO additionally applies unsupervised clustering to recover latent subpopulations when they are unavailable. On 7 diagnostic benchmarks covering 5 modalities (X-ray, CT, dermoscopy, mammography, ultrasound), EQPO reduces F1 standard deviation by 43.9% and the maximum cross-group F1 gap by 42.7% on QoQ-Med3-8B over vanilla GRPO, and narrows predictive parity gaps by 27.2% on MedGemma-4B over bias-mitigated RL baselines while raising F1 by 12.5% even without any demographic labels. Examining the training trajectory shows that EQPO steadily improves fairness over the course of optimization, in contrast to baseline methods whose fairness degrades as training proceeds, and the discovered implicit groups remain stable and align with masked demographic attributes. We further release EquiMedGemma-4B and EquiQoQ-Med3-8B, equitability-aware clinical VLLMs that attain state-of-the-art accuracy with markedly smaller demographic gaps.