BriefGPT.xyz
Mar, 2025
基于大型语言模型的科学主张验证的支持和反驳证据检索
LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification
HTML
PDF
Siyuan Wang, James R. Foulds, Md Osman Gani, Shimei Pan
TL;DR
本研究提出了CIBER(基于证据检索的主张调查),旨在解决大型语言模型在科学主张验证中固有的不确定性。CIBER通过分析模型对不同查询的反应一致性,优化了证据检索过程,并在多种科学领域中实现了更好的性能,具有重要的实际应用潜力。
Abstract
In this paper, we introduce CIBER (Claim Investigation Based on
Evidence Retrieval
), an extension of the Retrieval-Augmented Generation (RAG) framework designed to identify corroborating and refuting documents as evidence for
→