UMLS 注入语言模型做医学问答，研究了吗？未必——一篇批判性综述
Are We Done with UMLS Injection into Language Models for Medical Question Answering?
AI 导读
一篇 arXiv 综述论文重新审视将 Unified Medical Language System (UMLS) 知识图谱注入语言模型以提升医学问答（MQA）表现的做法，结论是这种注入通常只带来有限的性能提升。
正文 · 原文
Abstract:Maybe not. The Unified Medical Language System (UMLS) has become an oracle for millions of clinicians and health system developers worldwide. Researchers have increasingly used knowledge graphs derived from UMLS to enhance language models' factual accuracy and reasoning traceability in high-stakes tasks. Medical Question Answering (MQA) is a prime testbed for integration, with benchmarks usually involving professional exercises such as disease diagnosis and drug prescription from patient history. Despite the assumed benefits, empirical evidence shows that UMLS-based graph injection typically yields modest performance gains. This paper reviews existing MQA work, critically analyzing the selected UMLS sources and their usage with language models, and probes each of these choices in isolation. We uncover methodological issues never discussed in prior work, from low UMLS coverage to weak subgraph retrieval pipelines. Based on our findings, we provide actionable recommendations to unlock the untapped potential of UMLS as an external knowledge source.
| Comments: | 20 pages, 10 figures, 13 tables. Code and literature annotations: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33801 [cs.AI] |
| (or arXiv:2610.33801v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33801 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lorenzo Molfetta [view email]
[v1]
Sat, 24 Oct 2026 17:06:58 UTC (1,014 KB)
来源：arXiv cs.AI · arxiv.org