arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.18526cs.CLcs.AIcs.DL
收藏

SciClaims: 一种用于生物医学声明分析的端到端生成系统

SciClaims: An End-to-End Generative System for Biomedical Claim Analysis

Raúl Ortega, José Manuel Gómez-Pérez

AI总结:

SciClaims是一种基于大语言模型的端到端生物医学声明分析系统,可自动提取声明、检索证据并验证真实性,无需额外微调。

摘要:

我们介绍了SciClaims,一种用于生物医学领域端到端科学声明分析的交互式网页系统。该系统设计用于高风险应用场景,如系统性文献综述和专利验证。SciClaims从文本中提取声明,从PubMed检索相关证据,并验证其真实性。系统具有用户友好的界面,用户可以输入科学文本,查看提取的声明、预测、支持或反驳的证据以及自然语言的解释。与以往方法不同,SciClaims使用单一大语言模型无缝整合整个科学声明分析过程,无需额外微调。SciClaims优化以在单个GPU上高效运行,并已公开供实时交互使用。

英文摘要:

We present SciClaims, an interactive web-based system for end-to-end scientific claim analysis in the biomedical domain. Designed for high-stakes use cases such as systematic literature reviews and patent validation, SciClaims extracts claims from text, retrieves relevant evidence from PubMed, and verifies their veracity. The system features a user-friendly interface where users can input scientific text and view extracted claims, predictions, supporting or refuting evidence, and justifications in natural language. Unlike prior approaches, SciClaims seamlessly integrates the entire scientific claim analysis process using a single large language model, without requiring additional fine-tuning. SciClaims is optimized to run efficiently on a single GPU and is publicly available for live interaction.

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。

↑