MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering

TL;DR

MedCoT-RAG enhances medical question answering by integrating causal-aware retrieval with structured reasoning, significantly improving accuracy and interpretability over existing methods in clinical tasks.

Contribution

This paper introduces MedCoT-RAG, a novel framework combining causal document retrieval with chain-of-thought prompting tailored for medical workflows.

Findings

Outperforms baseline models by up to 10.3% in accuracy.

Improves interpretability and consistency in medical QA.

Effective across diverse medical benchmarks.

Abstract

Large language models (LLMs) have shown promise in medical question answering but often struggle with hallucinations and shallow reasoning, particularly in tasks requiring nuanced clinical understanding. Retrieval-augmented generation (RAG) offers a practical and privacy-preserving way to enhance LLMs with external medical knowledge. However, most existing approaches rely on surface-level semantic retrieval and lack the structured reasoning needed for clinical decision support. We introduce MedCoT-RAG, a domain-specific framework that combines causal-aware document retrieval with structured chain-of-thought prompting tailored to medical workflows. This design enables models to retrieve evidence aligned with diagnostic logic and generate step-by-step causal reasoning reflective of real-world clinical practice. Experiments on three diverse medical QA benchmarks show that MedCoT-RAG outperforms strong baselines by up to 10.3% over vanilla RAG and 6.4% over advanced domain-adapted methods, improving accuracy, interpretability, and consistency in complex medical tasks.