DeCode: Decoupling Content and Delivery for Medical QA

TL;DR

DeCode is a training-free framework that enhances large language models to generate more contextually relevant and clinically accurate answers in medical question answering tasks, significantly improving their zero-shot performance.

Contribution

DeCode introduces a novel, model-agnostic approach to adapt existing LLMs for better clinical relevance without additional training.

Findings

Boosts zero-shot performance from 28.4% to 49.8%.

Achieves new state-of-the-art on OpenAI HealthBench.

Improves clinical question answering accuracy.

Abstract

Large language models (LLMs) exhibit strong medical knowledge and can generate factually accurate responses. However, existing models often fail to account for individual patient contexts, producing answers that are clinically correct yet poorly aligned with patients' needs. In this work, we introduce DeCode (Decoupling Content and Delivery), a training-free, model-agnostic framework that adapts existing LLMs to produce contextualized answers in clinical settings. We evaluate DeCode on OpenAI HealthBench, a comprehensive and challenging benchmark designed to assess clinical relevance and validity of LLM responses. DeCode boosts zero-shot performance from 28.4% to 49.8% and achieves new state-of-the-art compared to existing methods. Experimental results suggest the effectiveness of DeCode in improving clinical question answering of LLMs.