# Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems

arXiv: https://arxiv.org/abs/2503.15454 · HTML: https://mlsanity.com/paper/2503.15454/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases](https://mlsanity.com/paper/2403.10446/) (2024)
- [A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models](https://mlsanity.com/paper/2403.12025/) (2024)
- [ComposerX: Multi-Agent Symbolic Music Composition with LLMs](https://mlsanity.com/paper/2404.18081/) (2024)
- [Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.15228/) (2025)
- [FairRAG: Fair Human Generation via Fair Retrieval Augmentation](https://mlsanity.com/paper/2403.19964/) (2024)
- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Enhance Image-to-Image Generation with LLaVA-generated Prompts](https://mlsanity.com/paper/2406.01956/) (2024)
- [Advances in APPFL: A Comprehensive and Extensible Federated Learning Framework](https://mlsanity.com/paper/2409.11585/) (2024)
- [HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models](https://mlsanity.com/paper/2412.19925/) (2024)
- [Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review](https://mlsanity.com/paper/2410.03663/) (2024)
- [Mix of Experts Language Model for Named Entity Recognition](https://mlsanity.com/paper/2404.19192/) (2024)
- [Trajectory Tracking Using Frenet Coordinates with Deep Deterministic Policy Gradient](https://mlsanity.com/paper/2411.13885/) (2024)
- ["Reasoning" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments](https://mlsanity.com/paper/2402.08498/) (2024)
- [GPTDrawer: Enhancing Visual Synthesis through ChatGPT](https://mlsanity.com/paper/2412.10429/) (2024)

## Built on by (most cited first, 6 of 6)

- [Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness](https://mlsanity.com/paper/2603.07368/) (2026)
- [Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning](https://mlsanity.com/paper/2601.20221/) (2026)
- [This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA](https://mlsanity.com/paper/2604.05051/) (2026)
- [An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2506.07411/) (2025)
- [Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model](https://mlsanity.com/paper/2607.01595/) (2026)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026)

## Abstract (arXiv)

Medical Question Answering systems based on Retrieval Augmented Generation is promising for clinical decision support because they can integrate external knowledge, thus reducing inaccuracies inherent in standalone large language models (LLMs). However, these systems may unintentionally propagate or amplify biases associated with sensitive demographic attributes like race, gender, and socioeconomic factors. This study systematically evaluates demographic biases within medical RAG pipelines across multiple QA benchmarks, including MedQA, MedMCQA, MMLU, and EquityMedQA. We quantify disparities in retrieval consistency and answer correctness by generating and analyzing queries sensitive to demographic variations. We further implement and compare several bias mitigation strategies to address identified biases, including Chain of Thought reasoning, Counterfactual filtering, Adversarial prompt refinement, and Majority Vote aggregation. Experimental results reveal significant demographic disparities, highlighting that Majority Vote aggregation notably improves accuracy and fairness metrics. Our findings underscore the critical need for explicitly fairness-aware retrieval methods and prompt engineering strategies to develop truly equitable medical QA systems.