arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.04978cs.CLcs.AI
收藏

基于知识图谱集成协作的增强型提示大语言模型推理方案

An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration

Beijing University of Posts and Telecommunications(北京邮电大学)

Yihao Li, Ru Zhang, Jianyi Liu

AI总结:

本文提出一种免训练的KG与LLM协作推理方案,通过迭代探索知识图谱、检索任务相关子图并结合LLM隐式知识进行可溯源推理,在多个数据集上取得显著提升,尤其在QALD10上超过最佳基线10%以上。

摘要:

尽管大语言模型(LLMs)在众多自然语言处理(NLP)任务中展现出卓越性能,但它们在实际应用中仍面临幻觉、知识更新不足以及推理过程透明度有限等挑战。为克服这些局限,本研究创新性地提出了一种免训练的协作推理方案,该方案涉及知识图谱(KG)与LLMs之间的紧密合作。该方案首先利用LLMs迭代探索KG,有选择地检索与任务相关的知识子图以支持推理。随后引导LLMs进一步结合自身固有的隐式知识,在子图上进行推理,同时明确阐述推理过程。通过这种协作方式,本方案实现了更可靠的基于知识的推理,并有助于对推理结果进行溯源。实验结果表明,本方案在多个数据集上取得了显著进展,尤其在QALD10数据集上,相较于最佳基线和微调后的最先进(SOTA)工作,实现了超过10%的提升。基于这一成果,本研究希望为未来KG与LLMs融合的研究提供有价值的参考,从而提升LLMs解决复杂问题的能力。

英文摘要:

While Large Language Models (LLMs) demonstrate exceptional performance in a multitude of Natural Language Processing (NLP) tasks, they encounter challenges in practical applications, including issues with hallucinations, inadequate knowledge updating, and limited transparency in the reasoning process. To overcome these limitations, this study innovatively proposes a collaborative training-free reasoning scheme involving tight cooperation between Knowledge Graph (KG) and LLMs. This scheme first involves using LLMs to iteratively explore KG, selectively retrieving a task-relevant knowledge subgraph to support reasoning. The LLMs are then guided to further combine inherent implicit knowledge to reason on the subgraph while explicitly elucidating the reasoning process. Through such a cooperative approach, our scheme achieves more reliable knowledge-based reasoning and facilitates the tracing of the reasoning results. Experimental results show that our scheme significantly progressed across multiple datasets, notably achieving over a 10% improvement on the QALD10 dataset compared to the best baseline and the fine-tuned state-of-the-art (SOTA) work. Building on this success, this study hopes to offer a valuable reference for future research in the fusion of KG and LLMs, thereby enhancing LLMs' proficiency in solving complex issues.

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。

↑