arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.00261cs.CLcs.AIcs.MM
收藏

面向心电图-语言模型的检索增强生成

Retrieval-Augmented Generation for Electrocardiogram-Language Models

Carnegie Mellon University(卡内基梅隆大学);Columbia University(哥伦比亚大学);Allegheny Health Network(阿勒格尼医疗网络);University of Colorado(科罗拉多大学)

Xiaoyu Song, William Han, Tony Chen, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Ding Zhao

AI总结:

针对当前缺乏面向心电图-语言模型的检索增强生成开源实现与系统研究的空白,该研究提出首个对应开源RAG流水线,经三个公开数据集验证,其性能优于无RAG的基线模型,明确了ELM设计关键要点。

摘要:

人们对生成式心电图-语言模型(Electrocardiogram-Language Models, ELMs)的兴趣日益浓厚,这类模型能根据心电信号和文本查询生成文本回复。与输出标签概率的传统分类器不同,ELMs功能更全面,既支持波形分析、诊断、预后等领域特定任务,也支持开放式问答、对话等通用任务。检索增强生成(Retrieval-Augmented Generation, RAG)被广泛应用于大语言模型(Large Language Models, LLMs)中,用于将LLM的输出锚定在检索到的知识上,有助于减少幻觉并提升自然语言生成(natural language generation, NLG)效果。然而,尽管RAG前景可观,目前尚无针对ELMs的RAG流水线设计的开源实现或系统性研究。为填补这一空白,我们提出了首个面向ELMs的开源RAG流水线,并提供了用于自然语言生成任务的基线与消融实验。在三个公开数据集上的实验表明,搭载RAG的ELMs性能始终优于无RAG的基线模型,同时明确了ELM设计的关键考量因素。我们的代码可在以下地址获取:https://github.com/willxxy/ECG-Bench。

英文摘要:

Interest in generative Electrocardiogram-Language Models (ELMs) is growing, as they can produce textual responses conditioned on ECG signals and textual queries. Unlike traditional classifiers that output label probabilities, ELMs are more versatile, supporting domain-specific tasks (e.g., waveform analysis, diagnosis, prognosis) as well as general tasks (e.g., open-ended questions, dialogue). Retrieval-Augmented Generation (RAG), widely used in Large Language Models (LLMs) to ground LLM outputs in retrieved knowledge, helps reduce hallucinations and improve natural language generation (NLG). However, despite its promise, no open-source implementation or systematic study of RAG pipeline design for ELMs currently exists. To address this gap, we present the first open-source RAG pipeline for ELMs, along with baselines and ablation studies for NLG. Experiments on three public datasets show that ELMs with RAG consistently improves performance over non-RAG baselines and highlights key ELM design considerations. Our code is available at: https://github.com/willxxy/ECG-Bench.

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。

↑