MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Shujun, Lin, Haokun, Wu, Yichen, Zhou, Yinan, Li, Zixuan, Wan, Zhongwei, Xing, Xingrun, Zheng, Yefeng, Li, Xiang, Shan, Caifeng, Sun, Zhenan, Li, Quanzheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911245776453632
author Xia, Shujun
Lin, Haokun
Wu, Yichen
Zhou, Yinan
Li, Zixuan
Wan, Zhongwei
Xing, Xingrun
Zheng, Yefeng
Li, Xiang
Shan, Caifeng
Sun, Zhenan
Li, Quanzheng
author_facet Xia, Shujun
Lin, Haokun
Wu, Yichen
Zhou, Yinan
Li, Zixuan
Wan, Zhongwei
Xing, Xingrun
Zheng, Yefeng
Li, Xiang
Shan, Caifeng
Sun, Zhenan
Li, Quanzheng
contents LLMs hold great promise for healthcare applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice. Model editing has emerged as a potential remedy without full retraining. While parameter-based editing often compromises locality and is thus ill-suited for the medical domain, retrieval-based editing offers a more viable alternative. However, it still faces two critical challenges: (1) representation overlap within the medical knowledge space often causes inaccurate retrieval and reduces editing accuracy; (2) existing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world medical applications. To address these challenges, we first construct MedVersa, an enhanced benchmark with broader coverage of medical subjects, designed to evaluate both single and batch edits under strict locality constraints. We then propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance. Experimental results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics and provides the first validated solution for batch-editing in medical LLMs. Our code and dataset are available at https://github.com/mylittleriver/MedREK.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
Xia, Shujun
Lin, Haokun
Wu, Yichen
Zhou, Yinan
Li, Zixuan
Wan, Zhongwei
Xing, Xingrun
Zheng, Yefeng
Li, Xiang
Shan, Caifeng
Sun, Zhenan
Li, Quanzheng
Computation and Language
Artificial Intelligence
LLMs hold great promise for healthcare applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice. Model editing has emerged as a potential remedy without full retraining. While parameter-based editing often compromises locality and is thus ill-suited for the medical domain, retrieval-based editing offers a more viable alternative. However, it still faces two critical challenges: (1) representation overlap within the medical knowledge space often causes inaccurate retrieval and reduces editing accuracy; (2) existing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world medical applications. To address these challenges, we first construct MedVersa, an enhanced benchmark with broader coverage of medical subjects, designed to evaluate both single and batch edits under strict locality constraints. We then propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance. Experimental results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics and provides the first validated solution for batch-editing in medical LLMs. Our code and dataset are available at https://github.com/mylittleriver/MedREK.
title MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.13500