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

Medical Question-Answering (QA) systems based on Retrieval-Augmented Generation (RAG) are promising for clinical decision support due to their capability to integrate external knowledge, thus reducing inaccuracies inherent in standalone large language models (LLMs). However, these systems may unintentionally propagate 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-including Chain-of-Thought reasoning, Counterfactual filtering, Adversarial prompt refinement, and Majority Vote aggregation-to address identified biases. Experimental results reveal significant demographic disparities, highlighting that Majority Vote aggregation 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.