arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02110cs.CLcs.AI
收藏

UniOQA:一个结合大型语言模型的知识图谱问答统一框架

UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models

Xidian University(西安电子科技大学)

Zhuoyang Li, Liran Deng, Hui Liu, Qiaoqiao Liu, Junzhao Du

AI总结:

本文提出UniOQA统一框架,结合大型语言模型与并行工作流,通过微调生成Cypher查询、实体关系替换算法、适配RAG及动态决策,在OwnThink知识图谱问答基准上取得最先进结果。

摘要:

OwnThink是近期推出的最广泛的中文开放域知识图谱。尽管此前已有针对OwnThink的问答(OQA)尝试,但现有研究在模型表示能力方面存在局限,对进一步提升问答整体准确性构成了挑战。在本文中,我们提出了UniOQA,这是一个集成了两个互补并行工作流的统一框架。与传统方法不同,UniOQA利用大型语言模型(LLM)进行精确问答,并引入直接答案预测过程作为高性价比的补充。首先,为了增强表示能力,我们微调LLM将问题翻译为Cypher查询语言(CQL),以解决语义理解受限和幻觉问题。随后,我们引入实体与关系替换算法,以确保生成的CQL可执行。同时,为提高问答整体准确性,我们进一步将检索增强生成(RAG)过程适配于知识图谱。最后,我们通过动态决策算法优化答案准确性。实验结果表明,UniOQA将SpCQL逻辑准确率提升至21.2%,执行准确率提升至54.9%,在该基准上取得了新的最先进结果。通过消融实验,我们深入探讨了UniOQA卓越的表示能力并量化了其性能突破。

英文摘要:

OwnThink stands as the most extensive Chinese open-domain knowledge graph introduced in recent times. Despite prior attempts in question answering over OwnThink (OQA), existing studies have faced limitations in model representation capabilities, posing challenges in further enhancing overall accuracy in question answering. In this paper, we introduce UniOQA, a unified framework that integrates two complementary parallel workflows. Unlike conventional approaches, UniOQA harnesses large language models (LLMs) for precise question answering and incorporates a direct-answer-prediction process as a cost-effective complement. Initially, to bolster representation capacity, we fine-tune an LLM to translate questions into the Cypher query language (CQL), tackling issues associated with restricted semantic understanding and hallucinations. Subsequently, we introduce the Entity and Relation Replacement algorithm to ensure the executability of the generated CQL. Concurrently, to augment overall accuracy in question answering, we further adapt the Retrieval-Augmented Generation (RAG) process to the knowledge graph. Ultimately, we optimize answer accuracy through a dynamic decision algorithm. Experimental findings illustrate that UniOQA notably advances SpCQL Logical Accuracy to 21.2% and Execution Accuracy to 54.9%, achieving the new state-of-the-art results on this benchmark. Through ablation experiments, we delve into the superior representation capacity of UniOQA and quantify its performance breakthrough.

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。

↑