AGENTiGraph:一个利用私有数据的基于LLM的聊天机器人的交互式知识图谱平台
AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data
AI总结:
本文提出AGENTiGraph,一个基于多智能体架构的交互式知识图谱平台,通过自然语言交互实现知识提取、整合与实时可视化,在复杂领域问答任务中显著优于零样本基线。
摘要:
大型语言模型(LLMs)在各种应用中展现了能力,但面临幻觉、推理能力有限和事实不一致等挑战,特别是在处理复杂、特定领域的任务(如问答QA)时。虽然知识图谱(KGs)已被证明有助于缓解这些问题,但关于LLMs与背景KGs结合的研究仍然有限。特别是用户可访问性和底层KG的灵活性尚未得到充分探索。我们引入了AGENTiGraph(Adaptive Generative ENgine for Task-based Interaction and Graphical Representation),这是一个通过自然语言交互进行知识管理的平台。它集成了知识提取、整合和实时可视化。AGENTiGraph采用多智能体架构来动态解释用户意图、管理任务并整合新知识,确保对不断演变的用户需求和数据上下文的适应性。我们的方法在知识图谱交互中表现出卓越的性能,特别是对于复杂的特定领域任务。在包含3500个测试用例的数据集上的实验结果表明,AGENTiGraph显著优于最先进的零样本基线,在任务分类中达到95.12%的准确率,在任务执行中达到90.45%的成功率。用户研究证实了其在实际场景中的有效性。为了展示其多功能性,我们将AGENTiGraph扩展到立法和医疗领域,构建了能够回答法律和医疗背景下复杂查询的专用KGs。
英文摘要:
Large Language Models~(LLMs) have demonstrated capabilities across various applications but face challenges such as hallucination, limited reasoning abilities, and factual inconsistencies, especially when tackling complex, domain-specific tasks like question answering~(QA). While Knowledge Graphs~(KGs) have been shown to help mitigate these issues, research on the integration of LLMs with background KGs remains limited. In particular, user accessibility and the flexibility of the underlying KG have not been thoroughly explored. We introduce AGENTiGraph (Adaptive Generative ENgine for Task-based Interaction and Graphical Representation), a platform for knowledge management through natural language interaction. It integrates knowledge extraction, integration, and real-time visualization. AGENTiGraph employs a multi-agent architecture to dynamically interpret user intents, manage tasks, and integrate new knowledge, ensuring adaptability to evolving user requirements and data contexts. Our approach demonstrates superior performance in knowledge graph interactions, particularly for complex domain-specific tasks. Experimental results on a dataset of 3,500 test cases show AGENTiGraph significantly outperforms state-of-the-art zero-shot baselines, achieving 95.12\% accuracy in task classification and 90.45\% success rate in task execution. User studies corroborate its effectiveness in real-world scenarios. To showcase versatility, we extended AGENTiGraph to legislation and healthcare domains, constructing specialized KGs capable of answering complex queries in legal and medical contexts.
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。