AI News HubLIVE
原文

RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge

RAG-Coding is an agentic method for automated ICD-10-CM coding that orchestrates four large language model (LLM) agents and grounds decisions in external knowledge sources, improving coding accuracy and clinical compliance. On the MDACE dataset, it outperforms the best LLM baseline by 8-13% micro-F1 and 2-8% macro-F1. Compared to PLM-ICD, RAG-Coding shows higher micro recall (+11%) but lower micro precision (-6%), with comparable F1 scores. Ablation studies confirm the importance of external knowledge. The authors also release MDACE-2025, updated with expert re-annotations based on 2025 guidelines, enabling finer-grained evaluation.

Article intelligence

EngineersAdvanced

Key points

  • RAG-Coding uses four LLM agents and external knowledge sources to improve ICD-10-CM coding accuracy.
  • On the MDACE dataset, it outperforms the best LLM baseline by 8-13% micro-F1 and 2-8% macro-F1.
  • Compared to PLM-ICD, RAG-Coding achieves higher micro recall but lower micro precision, with comparable overall F1.
  • The MDACE-2025 dataset is released, re-annotated with 2025 guidelines for more detailed code labels.

Why it matters

This matters because RAG-Coding uses four LLM agents and external knowledge sources to improve ICD-10-CM coding accuracy.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.27377] RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge

[Submitted on 9 Apr 2026]

Title:RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge

View a PDF of the paper titled RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge, by Yidong Gan and 6 other authors

View PDF HTML (experimental)

Abstract:We present RAG-Coding, an agentic method for automated ICD-10-CM coding. RAG-Coding orchestrates four large language model (LLM) agents and grounds their coding decisions in external knowledge sources (e.g. the official coding tabular list and guidelines). By retrieving and cross-referencing relevant knowledge in these sources, the agents enhance coding accuracy and ensure clinical compliance. On the MDACE dataset, RAG-Coding outperforms the best LLM-based baseline by 8-13\% in micro-F1 and 2-8\% in macro-F1 across multiple LLM backbones. Compared to the state-of-the-art pretrained language model method, PLM-ICD, RAG-Coding exhibits higher micro recall (+11\%), while PLM-ICD exhibits higher micro precision (+6\%), yielding comparable micro- and macro-F1. Ablations show stepwise gains, highlighting the importance of incorporating external knowledge. We also release MDACE-2025, updating the original dataset with expert re-annotations with the latest 2025 ICD-10-CM guidelines. This update features more fine-grained code labels and enables evaluation against current clinical standards.

Comments: Additional experiments and analyses are in progress

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)

Cite as: arXiv:2605.27377 [cs.CL]

(or arXiv:2605.27377v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.27377

arXiv-issued DOI via DataCite

Submission history

From: Yidong Gan [view email] [v1] Thu, 9 Apr 2026 06:27:03 UTC (306 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge, by Yidong Gan and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.IR

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)