---
id: 20260529-T0-17
title: "RAG-Coding：结合外部知识提升LLM医疗编码准确性"
title_en: "RAG-Coding: Boosts LLM Medical Coding Accuracy with External Knowledge"
url: https://ai.daily.yangsir.net/daily/20260529-T0-17
issue_date: 2026-05-29
publish_date: 2026-05-28T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2605.27377
---

# RAG-Coding：结合外部知识提升LLM医疗编码准确性

斯坦福团队开发RAG-Coding系统，通过四个LLM智能体协作实现自动化ICD-10-CM医疗编码。该技术将编码决策锚定在官方编码表和临床指南等结构化外部知识源上，显著提升编码准确率。相比传统单模型方案，RAG-Coding在真实医疗数据测试中错误率降低30%，为医疗AI应用提供更可靠的编码解决方案。

## English Version

**RAG-Coding: Boosts LLM Medical Coding Accuracy with External Knowledge**

Stanford's RAG-Coding system automates ICD-10-CM medical coding using four LLM agents that ground decisions in structured external knowledge sources like official coding tables. This approach reduces errors by 30% compared to single-model systems in real medical data tests, providing a more reliable solution for healthcare AI applications.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2605.27377)

**详情页**：https://ai.daily.yangsir.net/daily/20260529-T0-17

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*