arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.18537cs.CL
收藏

通过自适应多方面检索增强利用大语言模型进行知识图谱问答

Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation

University of Science and Technology of China(中国科学技术大学);City University of Hong Kong(香港城市大学);Jarvis Research Center(贾维斯研究中心);Tencent YouTu Lab(腾讯优图实验室);Peking University(北京大学)

Derong Xu, Xinhang Li, Ziheng Zhang, Zhenxi Lin, Zhihong Zhu, Zhi Zheng, Xian Wu, Xiangyu Zhao, Tong Xu, Enhong Chen

AI总结:

本文提出 Amar 框架,通过实体、关系和子图的自对齐与相关性软门控减少检索噪声,在 WebQSP 和 CWQ 上提升知识图谱问答准确率及逻辑形式生成。

摘要:

大语言模型(LLM)展现出卓越能力,但在承担复杂知识推理任务时会受到幻觉和知识过时的困扰,从而产生事实错误的输出。此前研究试图通过从大规模知识图谱(KG)中检索事实知识来缓解这一问题,以辅助 LLM 进行逻辑推理和答案预测。然而,这类方法往往会引入噪声和无关数据,尤其是在存在来自多个知识方面的大量上下文的情况下。这样一来,LLM 的注意力可能会被从问题和相关信息上误导。在本研究中,我们提出了一种基于知识图谱的自适应多方面检索增强(Adaptive Multi-Aspect Retrieval-augmented over KGs,Amar)框架。该方法检索包括实体、关系和子图在内的知识,并将每一段检索到的文本转换为提示嵌入。Amar 框架包含两个关键子组件:1)自对齐模块,用于对齐实体、关系和子图之间的共性,以增强检索文本,从而降低噪声干扰;2)相关性门控模块,采用软门来学习问题与多方面检索数据之间的相关性分数,以决定哪些信息应当用于增强 LLM 的输出,甚至将哪些信息完全过滤。我们的方法在 WebQSP 和 CWQ 两个常用数据集上取得了最先进性能,准确率比最强竞争对手高 1.9%,逻辑形式生成相比直接将检索文本用作上下文提示的方法提升 6.6%。这些结果证明了 Amar 在改进 LLM 推理方面的有效性。

英文摘要:

Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted to mitigate it by retrieving factual knowledge from large-scale knowledge graphs (KGs) to assist LLMs in logical reasoning and prediction of answers. However, this kind of approach often introduces noise and irrelevant data, especially in situations with extensive context from multiple knowledge aspects. In this way, LLM attention can be potentially mislead from question and relevant information. In our study, we introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework. This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings. The Amar framework comprises two key sub-components: 1) a self-alignment module that aligns commonalities among entities, relations, and subgraphs to enhance retrieved text, thereby reducing noise interference; 2) a relevance gating module that employs a soft gate to learn the relevance score between question and multi-aspect retrieved data, to determine which information should be used to enhance LLMs' output, or even filtered altogether. Our method has achieved state-of-the-art performance on two common datasets, WebQSP and CWQ, showing a 1.9\% improvement in accuracy over its best competitor and a 6.6\% improvement in logical form generation over a method that directly uses retrieved text as context prompts. These results demonstrate the effectiveness of Amar in improving the reasoning of LLMs.

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。

↑