研究大模型在生物医学术语链接中的失败原因，发现标识符曝光度最关键。
Predicting Failures of LLMs to Link Biomedical Ontology Terms to Identifiers Evidence Across Models and Ontologies
- 对比两大语料库与两模型，分析术语链接失败因素。
- 暴露于标识符是预测链接成功最强的单一因素。
- 适合关注AI医疗准确性与知识融合的研究者阅读。
大型语言模型在生物医学自然语言处理任务中表现良好，但常无法将术语正确链接到其标识符。本研究通过分析两个主要本体（人类表型本体和基因本体）及两种高性能模型（GPT-4o 和 LLaMa 3.1 405B），评估九个相关特征（包括术语熟悉度、标识符使用频率、形态学特征和本体结构）。单变量与多变量分析表明，模型对本体标识符的暴露程度是预测链接成功率最强的因素。
原文摘要 · Abstract (English)
Large language models often perform well on biomedical NLP tasks but may fail to link ontology terms to their correct identifiers. We investigate why these failures occur by analyzing predictions across two major ontologies, Human Phenotype Ontology and Gene Ontology, and two high-performing models, GPT-4o and LLaMa 3.1 405B. We evaluate nine candidate features related to term familiarity, identifier usage, morphology, and ontology structure. Univariate and multivariate analyses show that exposure to ontology identifiers is the strongest predictor of linking success.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。