MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
Columbia University · Institute of Automation, CAS & City University of Hong Kong · City University of Hong Kong · City University of Hong Kong · NLPR, Institute of automation, Chinese academy of science · Ohio State University, Columbus · Institute of automation, Chinese academy of science, Chinese Academy of Sciences · Westlake University · Massachusetts General Hospital and Harvard Medical School · Nanjing University · Chinese of Academy of Sciences · Mass General Hospital, Harvard Medical School
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
LLMs hold great promise for healthcare applications, but fast-changing medical knowledge can quickly make their outputs outdated or inaccurate, limiting use in high-stakes settings. Model editing can update LLMs without full retraining, but parameter-based methods often break locality and are risky in medicine, making retrieval-based editing a better fit. However, applying model editing methods to the medical domain has two key challenges: (1) retrieval-based methods suffer from representation overlap within the medical knowledge space that causes inaccurate retrieval and reduces editing accuracy; (2) existing medical editing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world applications. To address these challenges, we construct MedVersa, an expanded benchmark that evaluates single and batch edits across broader medical coverage 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. Experiments across various medical benchmarks show that our MedREK consistently improves key metrics and provides the first validated solution for batch editing in medical LLMs.