# DeCode: Decoupling Content and Delivery for Medical QA

Source: [DeCode: Decoupling Content and Delivery for Medical QA](<https://www.sota2.com/research/paper/695c970353fdd5c361743703>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T05:00:04.157Z

Authors: Po-Jen Ko, Chen-Han Tsai, Yu-Shao Peng

Published: 2026-01-05T13:54:38.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.02123>)

[PDF](<https://arxiv.org/pdf/2601.02123.pdf>)
