KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models

doi:10.3390/electronics13234835

	KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models
	Hou, Kun 1; Li, Jingyuan 1; Liu, Yingying 1; Sun, Shiqi 2; Zhang, Haoliang 1; Jiang, Haiyang 1
	2024-12-01
发表期刊	ELECTRONICS
ISSN	2079-9292
卷号	13 期号:23 页码:23
摘要	Despite the remarkable progress of large language models (LLMs) in understanding and generating unstructured text, their application in structured data domains and their multi-role capabilities remain underexplored. In particular, utilizing LLMs to perform complex reasoning tasks on knowledge graphs (KGs) is still an emerging area with limited research. To address this gap, we propose KG-EGV, a versatile framework leveraging LLMs to perform KG-based tasks. KG-EGV consists of four core steps: sentence segmentation, graph retrieval, EGV, and backward updating, each designed to segment sentences, retrieve relevant KG components, and derive logical conclusions. EGV, a novel integrated framework for LLM inference, enables comprehensive reasoning beyond retrieval by synthesizing diverse evidence, which is often unattainable via retrieval alone due to noise or hallucinations. The framework incorporates six key stages: generation expansion, expansion evaluation, document re-ranking, re-ranking evaluation, answer generation, and answer verification. Within this framework, LLMs take on various roles, such as generator, re-ranker, evaluator, and verifier, collaboratively enhancing answer precision and logical coherence. By combining the strengths of retrieval-based and generation-based evidence, KG-EGV achieves greater flexibility and accuracy in evidence gathering and answer formulation. Extensive experiments on widely used benchmarks, including FactKG, MetaQA, NQ, WebQ, and TriviaQA, demonstrate that KG-EGV achieves state-of-the-art performance in answer accuracy and evidence quality, showcasing its potential to advance QA research and applications.
关键词	knowledge graph large language model question answering evidence retrieval multi-role reasoning answer verification ODQA graph-based inference
DOI	10.3390/electronics13234835
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China ; Henan Province Key Research and Development Project[241111211900] ; Ministry of Education Industry Education - Tencent[2307000062303144] ; [62172393]
WOS研究方向	Computer Science ; Engineering ; Physics
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Physics, Applied
WOS记录号	WOS:001377775000001
出版者	MDPI
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41057
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Jingyuan
作者单位	1.Beijing Technol & Business Univ, Sch Comp & Artificial Intelligence, Beijing 102401, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Hou, Kun,Li, Jingyuan,Liu, Yingying,et al. KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models[J]. ELECTRONICS,2024,13(23):23.
APA	Hou, Kun,Li, Jingyuan,Liu, Yingying,Sun, Shiqi,Zhang, Haoliang,&Jiang, Haiyang.(2024).KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models.ELECTRONICS,13(23),23.
MLA	Hou, Kun,et al."KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models".ELECTRONICS 13.23(2024):23.