CLAIOct 15, 2025

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

arXiv:2510.13500v21 citationsh-index: 14Has Code
Originality Incremental advance
AI Analysis

This work addresses critical challenges in applying LLMs to high-stakes clinical practice by improving editing accuracy and scalability, though it is incremental in advancing retrieval-based methods.

The paper tackled the problem of outdated or inaccurate information in medical LLMs by proposing MedREK, a retrieval-based editing framework that addresses representation overlap and enables batch-editing, achieving superior performance on medical benchmarks.

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applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice.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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes