| 本文已被：浏览 1934次 下载 2628次 |
码上扫一扫！ |
|
|
| 基于相关性提示的知识图谱问答 |
|
马杰1,2, 孙望淳1,2, 王平辉1,2, 张若非1,2, 李帅鹏2, 苏洲1,2
|
|
1.西安交通大学 网络空间安全学院, 陕西 西安 710049;2.智能网络与网络安全教育部重点实验室(西安交通大学), 陕西 西安 710049
|
|
| 摘要: |
| 大语言模型(large language model, LLM)随着不断发展, 在开放领域取得了出色的表现. 然而, 由于缺乏专业知识, LLM在垂直领域问答任务上效果较差. 这一问题引发了研究者的广泛关注. 现有研究通过“检索-问答”的方式, 将领域知识注入大语言模型, 以增强其性能. 然而该方式通常会检索到额外的噪声数据而导致LLM的性能损失. 为了解决该问题, 提出基于知识相关性的知识图谱问答方法. 具体而言, 将噪声数据与回答问题所需要的知识进行区分, 在“检索-相关性评估-问答”的框架下, 引导大语言模型选择合理的知识做出正确的回答. 此外, 提出一个机械领域知识图谱问答的数据集Mecha-QA, 包含传统机械制造以及增材制造两个子领域, 以推进该领域大语言模型与知识图谱问答相关的研究. 为了验证所提方法的有效性, 在Mecha-QA和航空航天领域数据集Aero-QA上进行实验. 结果表明, 该方法可以显著提升大语言模型在垂直领域知识图谱问答的性能. |
| 关键词: 大语言模型 知识图谱 垂直领域 问答系统 知识检索 |
| DOI：10.13328/j.cnki.jos.007247 |
| 分类号:TP18 |
| 基金项目:国家重点研发计划(2021YFB1715600); 国家自然科学基金(62306229) |
|
| Knowledge Graph Question Answering Based on Relevance Prompts |
|
MA Jie1,2, SUN Wang-Chun1,2, WANG Ping-Hui1,2, ZHANG Ruo-Fei1,2, LI Shuai-Peng2, SU Zhou1,2
|
|
1.School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China;2.Ministry of Education Key Laboratory for Intelligent Networks and Network Security (Xi’an Jiaotong University), Xi’an 710049, China
|
| Abstract: |
| As large language models (LLMs) continue to evolve, they have shown impressive performance in open-domain tasks. However, they exhibit limited effectiveness in domain-specific question-answering due to a lack of domain-specific knowledge. This limitation has attracted widespread attention from researchers in the field. Current research attempts to infuse domain knowledge into LLMs through a retrieve-answer approach to enhance their performance. However, this method often retrieves additional, irrelevant data, leading to a degradation in LLM effectiveness. Therefore, this study proposes a method for knowledge graph question answering based on the relevance of knowledge. This method focuses on distinguishing essential knowledge required for specific questions from noisy data. Under a framework of retrieval-relevance assessment-answering, this method guides LLMs to select appropriate knowledge for accurate answers. Moreover, this study introduces a dataset named Mecha-QA for question-answering using a mechanical domain knowledge graph, covering traditional machinery manufacturing and additive manufacturing, to promote research that integrates LLMs with knowledge graph question answering in this field. To validate the effectiveness of the proposed method, experiments are conducted on the Aero-QA dataset in the aerospace domain and the Mecha-QA dataset. Results demonstrate that the proposed method significantly improves the performance of LLMs in knowledge graph question answering in vertical domains. |
| Key words: large language model (LLM) knowledge graph (KG) vertical domain question answering system knowledge retrieval |
