arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.07500cs.IRcs.AIcs.CL
收藏

PromptLink:利用大语言模型实现跨来源生物医学概念链接

PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking

Emory University(埃默里大学)

Yuzhang Xie, Jiaying Lu, Joyce Ho, Fadi Nahab, Xiao Hu, Carl Yang

AI总结:

针对跨数据源生物医学概念链接的命名差异与现有方法泛化性差的问题,提出结合生物医学预训练模型候选生成与LLM两阶段提示反思的PromptLink框架,在EHR与KG链接任务上验证了有效性且具备通用性。

摘要:

跨不同数据源链接(对齐)生物医学概念可支撑多种整合分析,但由于概念命名规范存在差异,该任务极具挑战性。目前已开发出多种策略应对这一挑战,例如基于字符串匹配规则的方法、人工构建的叙词表以及机器学习模型。但这些方法受限于有限的先验生物医学知识,难以在有限的规则、叙词表或训练样本之外实现泛化。近年来,大语言模型(LLM)凭借其前所未有的丰富先验知识和强大的零样本预测能力,在各类生物医学自然语言处理任务中取得了令人瞩目的成果。然而,LLM存在成本高、上下文长度有限以及预测不可靠等问题。本研究提出了一种新型生物医学概念链接框架PromptLink,该框架借助LLM实现功能。它首先采用生物医学专用预训练语言模型生成可适配LLM上下文窗口的候选概念;随后通过两阶段提示词利用LLM完成概念链接,其中第一阶段提示词旨在从LLM中调取生物医学先验知识以完成概念链接任务,第二阶段提示词则促使LLM对自身预测结果进行反思,以进一步提升预测可靠性。在两个电子健康记录(EHR)数据集与一个外部生物医学知识图谱(KG)之间的概念链接任务上的实证结果,证明了PromptLink的有效性。此外,PromptLink是一个通用框架,无需依赖额外的先验知识、上下文或训练数据,非常适用于各类数据源之间的概念链接任务。其源代码可在https://github.com/constantjxyz/PromptLink获取。

英文摘要:

Linking (aligning) biomedical concepts across diverse data sources enables various integrative analyses, but it is challenging due to the discrepancies in concept naming conventions. Various strategies have been developed to overcome this challenge, such as those based on string-matching rules, manually crafted thesauri, and machine learning models. However, these methods are constrained by limited prior biomedical knowledge and can hardly generalize beyond the limited amounts of rules, thesauri, or training samples. Recently, large language models (LLMs) have exhibited impressive results in diverse biomedical NLP tasks due to their unprecedentedly rich prior knowledge and strong zero-shot prediction abilities. However, LLMs suffer from issues including high costs, limited context length, and unreliable predictions. In this research, we propose PromptLink, a novel biomedical concept linking framework that leverages LLMs. It first employs a biomedical-specialized pre-trained language model to generate candidate concepts that can fit in the LLM context windows. Then it utilizes an LLM to link concepts through two-stage prompts, where the first-stage prompt aims to elicit the biomedical prior knowledge from the LLM for the concept linking task and the second-stage prompt enforces the LLM to reflect on its own predictions to further enhance their reliability. Empirical results on the concept linking task between two EHR datasets and an external biomedical KG demonstrate the effectiveness of PromptLink. Furthermore, PromptLink is a generic framework without reliance on additional prior knowledge, context, or training data, making it well-suited for concept linking across various types of data sources. The source code is available at https://github.com/constantjxyz/PromptLink.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑