OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System

arXiv - CS - Information Retrieval Pub Date : 2024-09-09 DOI:arxiv-2409.07497

Ningyu Zhang, Zekun Xi, Yujie Luo, Peng Wang, Bozhong Tian, Yunzhi Yao, Jintian Zhang, Shumin Deng, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen

{"title":"OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System","authors":"Ningyu Zhang, Zekun Xi, Yujie Luo, Peng Wang, Bozhong Tian, Yunzhi Yao, Jintian Zhang, Shumin Deng, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen","doi":"arxiv-2409.07497","DOIUrl":null,"url":null,"abstract":"Knowledge representation has been a central aim of AI since its inception.\nSymbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can\nboth represent knowledge. KGs provide highly accurate and explicit knowledge\nrepresentation, but face scalability issue; while LLMs offer expansive coverage\nof knowledge, but incur significant training costs and struggle with precise\nand reliable knowledge manipulation. To this end, we introduce OneEdit, a\nneural-symbolic prototype system for collaborative knowledge editing using\nnatural language, which facilitates easy-to-use knowledge management with KG\nand LLM. OneEdit consists of three modules: 1) The Interpreter serves for user\ninteraction with natural language; 2) The Controller manages editing requests\nfrom various users, leveraging the KG with rollbacks to handle knowledge\nconflicts and prevent toxic knowledge attacks; 3) The Editor utilizes the\nknowledge from the Controller to edit KG and LLM. We conduct experiments on two\nnew datasets with KGs which demonstrate that OneEdit can achieve superior\nperformance.","PeriodicalId":501281,"journal":{"name":"arXiv - CS - Information Retrieval","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07497","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge representation, but face scalability issue; while LLMs offer expansive coverage of knowledge, but incur significant training costs and struggle with precise and reliable knowledge manipulation. To this end, we introduce OneEdit, a neural-symbolic prototype system for collaborative knowledge editing using natural language, which facilitates easy-to-use knowledge management with KG and LLM. OneEdit consists of three modules: 1) The Interpreter serves for user interaction with natural language; 2) The Controller manages editing requests from various users, leveraging the KG with rollbacks to handle knowledge conflicts and prevent toxic knowledge attacks; 3) The Editor utilizes the knowledge from the Controller to edit KG and LLM. We conduct experiments on two new datasets with KGs which demonstrate that OneEdit can achieve superior performance.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

OneEdit：神经符号协作知识编辑系统

符号知识图谱（KG）和神经大语言模型（LLM）都可以表示知识。符号知识图谱（KGs）和神经大语言模型（LLMs）都可以表示知识。KGs 提供了高度准确和明确的知识表示，但面临可扩展性问题；而 LLMs 提供了广阔的知识覆盖范围，但会产生巨大的训练成本，并且在精确和可靠的知识操作方面存在困难。为此，我们介绍了一个使用自然语言进行协作知识编辑的神经符号原型系统--OneEdit，它可以方便地使用KG和LLM进行知识管理。OneEdit 由三个模块组成：1）解释器（Interpreter）用于用户与自然语言的交互；2）控制器（Controller）管理来自不同用户的编辑请求，利用带有回滚功能的知识库（KG）来处理知识冲突并防止有毒知识攻击；3）编辑器（Editor）利用来自控制器的知识来编辑知识库和 LLM。我们在两个带有知识库的新数据集上进行了实验，结果表明 OneEdit 可以实现卓越的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

arXiv - CS - Information Retrieval

自引率

0.00%

发文量