arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.07677cs.CLcs.AI
收藏

ODA:集成LLM与知识图谱的观察驱动智能体

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

Panasonic Connect Co., Ltd.(松下连接公司);Peking University(北京大学)

Lei Sun, Zhengwei Tao, Youdi Li, Hiroshi Arakawa

AI总结:

提出观察驱动智能体框架ODA,通过递归全局观察机制将知识图谱推理能力整合进行动与反思模块,在多个数据集上实现SOTA性能。

摘要:

大语言模型(LLMs)与知识图谱(KGs)的集成在各类自然语言处理任务中取得了显著成功。然而,现有集成方法通常仅依据LLM对问题的分析来引导任务求解过程,忽视了KGs所蕴含的海量知识中固有的丰富认知潜力。为此,我们提出观察驱动智能体(ODA),一种专为涉及KG的任务定制的新型AI智能体框架。ODA通过全局观察引入KG推理能力,利用观察、行动与反思的循环范式增强推理能力。针对观察期间知识的指数级爆炸问题,我们创新性地设计了递归观察机制。随后,将观察到的知识整合至行动与反思模块中。通过大量实验,ODA在多个数据集上展现出最先进的性能,准确率分别提升了12.87%和8.9%。

英文摘要:

The integration of Large Language Models (LLMs) and knowledge graphs (KGs) has achieved remarkable success in various natural language processing tasks. However, existing methodologies that integrate LLMs and KGs often navigate the task-solving process solely based on the LLM's analysis of the question, overlooking the rich cognitive potential inherent in the vast knowledge encapsulated in KGs. To address this, we introduce Observation-Driven Agent (ODA), a novel AI agent framework tailored for tasks involving KGs. ODA incorporates KG reasoning abilities via global observation, which enhances reasoning capabilities through a cyclical paradigm of observation, action, and reflection. Confronting the exponential explosion of knowledge during observation, we innovatively design a recursive observation mechanism. Subsequently, we integrate the observed knowledge into the action and reflection modules. Through extensive experiments, ODA demonstrates state-of-the-art performance on several datasets, notably achieving accuracy improvements of 12.87% and 8.9%.

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。

↑