发表机构
School of Computer Science and Engineering, Southeast University; Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学计算机科学与工程学院; 教育部新一代人工智能技术及其跨学科应用重点实验室（东南大学））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型在不确定知识图谱上问答时的问题，提出Debate-on-Graph框架，设计启发式搜索算法提取子图并引入多智能体辩论机制，经实验验证该框架能实现可靠且自适应推理，性能优于现有方法。
AI 中文摘要
大语言模型在自然语言处理中能力卓越，但在问答任务中常出现幻觉和知识缺失问题。知识图谱虽用于增强大语言模型推理，然而常含噪声和错误，现有方法无法识别过滤，会放大幻觉。不确定知识图谱为解决此挑战提供方向。本文提出Debate-on-Graph（DoG）框架，先设计针对不确定知识图谱的启发式搜索算法提取可靠且与问题相关的子图，减少噪声。接着引入多智能体辩论机制，通过自适应对抗辩论得出可靠答案。在四个基准问答数据集上的实验表明，DoG性能优于现有方法，实现可靠且自适应推理。
英文摘要
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge graphs (UKGs), which associate each triple with a confidence score to quantify uncertainty, offer a promising direction to address this challenge. Compared with prior work, we investigate how to leverage UKGs to support LLMs for QA. We propose Debate-on-Graph (DoG), a new framework that enables LLMs and UKGs to collaborate adaptively for reliable reasoning. Specifically, we first design a heuristic search algorithm tailored for UKGs to extract reliable and question-relevant subgraphs, thereby reducing noise and errors in retrieved knowledge. We then introduce a Multi-Agent Debate mechanism, which yields reliable answers through adaptive adversarial debates, aiming to fully exploit the knowledge in UKGs while preserving the reliability of retrieved evidence. Extensive experiments on four benchmark QA datasets show that DoG achieves state-of-the-art performance over existing LLM reasoning methods and KG-based baselines, while enabling reliable and adaptive reasoning. Our code is available at https://github.com/seucoin/Debate-on-Graph.
Comments18 pages, Accepted by ECML-PKDD 2026
