基于可追溯 LLM 的知识图谱语句验证

Daniel Adam, Tomáš Kliegr
{"title":"基于可追溯 LLM 的知识图谱语句验证","authors":"Daniel Adam, Tomáš Kliegr","doi":"arxiv-2409.07507","DOIUrl":null,"url":null,"abstract":"This article presents a method for verifying RDF triples using LLMs, with an\nemphasis on providing traceable arguments. Because the LLMs cannot currently\nreliably identify the origin of the information used to construct the response\nto the user query, our approach is to avoid using internal LLM factual\nknowledge altogether. Instead, verified RDF statements are compared to chunks\nof external documents retrieved through a web search or Wikipedia. To assess\nthe possible application of this workflow on biosciences content, we evaluated\n1,719 positive statements from the BioRED dataset and the same number of newly\ngenerated negative statements. The resulting precision is 88%, and recall is\n44%. This indicates that the method requires human oversight. We demonstrate\nthe method on Wikidata, where a SPARQL query is used to automatically retrieve\nstatements needing verification. Overall, the results suggest that LLMs could\nbe used for large-scale verification of statements in KGs, a task previously\nunfeasible due to human annotation costs.","PeriodicalId":501479,"journal":{"name":"arXiv - CS - Artificial Intelligence","volume":"96 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Traceable LLM-based validation of statements in knowledge graphs\",\"authors\":\"Daniel Adam, Tomáš Kliegr\",\"doi\":\"arxiv-2409.07507\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article presents a method for verifying RDF triples using LLMs, with an\\nemphasis on providing traceable arguments. Because the LLMs cannot currently\\nreliably identify the origin of the information used to construct the response\\nto the user query, our approach is to avoid using internal LLM factual\\nknowledge altogether. Instead, verified RDF statements are compared to chunks\\nof external documents retrieved through a web search or Wikipedia. To assess\\nthe possible application of this workflow on biosciences content, we evaluated\\n1,719 positive statements from the BioRED dataset and the same number of newly\\ngenerated negative statements. The resulting precision is 88%, and recall is\\n44%. This indicates that the method requires human oversight. We demonstrate\\nthe method on Wikidata, where a SPARQL query is used to automatically retrieve\\nstatements needing verification. Overall, the results suggest that LLMs could\\nbe used for large-scale verification of statements in KGs, a task previously\\nunfeasible due to human annotation costs.\",\"PeriodicalId\":501479,\"journal\":{\"name\":\"arXiv - CS - Artificial Intelligence\",\"volume\":\"96 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07507\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07507","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文介绍了一种使用 LLM 验证 RDF 三元组的方法,重点在于提供可追溯的论据。由于 LLM 目前无法可靠地识别用于构建用户查询响应的信息来源,我们的方法是完全避免使用 LLM 内部的事实知识。取而代之的是,将经过验证的 RDF 语句与通过网络搜索或维基百科检索到的外部文档块进行比较。为了评估这一工作流程在生物科学内容上的可能应用,我们评估了来自 BioRED 数据集的 1719 条正面语句和相同数量的新生成的负面语句。结果精确度为 88%,召回率为 44%。这表明该方法需要人为监督。我们在维基数据上演示了该方法,使用 SPARQL 查询自动检索需要验证的声明。总之,结果表明 LLM 可以用于大规模验证 KG 中的语句,而由于人工标注成本的原因,这项任务以前是不可行的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Traceable LLM-based validation of statements in knowledge graphs
This article presents a method for verifying RDF triples using LLMs, with an emphasis on providing traceable arguments. Because the LLMs cannot currently reliably identify the origin of the information used to construct the response to the user query, our approach is to avoid using internal LLM factual knowledge altogether. Instead, verified RDF statements are compared to chunks of external documents retrieved through a web search or Wikipedia. To assess the possible application of this workflow on biosciences content, we evaluated 1,719 positive statements from the BioRED dataset and the same number of newly generated negative statements. The resulting precision is 88%, and recall is 44%. This indicates that the method requires human oversight. We demonstrate the method on Wikidata, where a SPARQL query is used to automatically retrieve statements needing verification. Overall, the results suggest that LLMs could be used for large-scale verification of statements in KGs, a task previously unfeasible due to human annotation costs.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Abductive explanations of classifiers under constraints: Complexity and properties Explaining Non-monotonic Normative Reasoning using Argumentation Theory with Deontic Logic Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach A Metric Hybrid Planning Approach to Solving Pandemic Planning Problems with Simple SIR Models Neural Networks for Vehicle Routing Problem
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1