通过同侪上下文异常检测减少基于LLM的科学文献分析中的幻觉
Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection
AI总结：
本文提出Peer Context Outlier Detection方法，通过文档间关系提升数据提取准确性，实验显示在6个科学领域达到98%的异常检测精度，减少幻觉并提高自动化系统可信度。
摘要：
减少大型语言模型（LLM）中的幻觉对于提高从大规模文本语料库中提取数据的准确性至关重要。当前方法如提示工程和思维链提示，侧重于单个文档，但未能考虑语料库中的关系。本文介绍Peer Context Outlier Detection（P-COD），一种利用文档间关系提升提取准确性的新方法。我们的应用领域是科学文献摘要，其中具有相似实验设置的论文应得出相似结论。通过将提取的数据与语料库中已验证的同侪信息进行比较，我们调整置信度分数并标记低置信度结果供专家审查。高置信度结果，通过同侪验证支持，被视为可靠。我们的实验显示，在6个科学领域中，异常检测的精度高达98%，证明我们的设计减少了幻觉，增强了自动化系统的可信度，并使研究人员能够专注于模糊情况，从而优化数据提取流程。
英文摘要：
Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents and fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), which uses inter-document relationships to improve extraction accuracy in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. Our experiments demonstrate up to 98% precision in outlier detection across 6 scientific domains, reducing hallucinations and letting researchers focus on genuinely ambiguous cases.
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。
