Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models
作者: Chenhui Liu, Jianpeng Zhou, Jiahai Wang
分类: cs.AI
发布日期: 2026-08-24
💡 一句话要点
提出关系中心探索框架以解决复杂知识图谱问答问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 知识图谱问答 多跳推理 关系中心探索 组合关系链 大型语言模型 信息检索 智能问答系统
📋 核心要点
- 现有方法在候选检索中依赖实体中心探索,导致不可靠的实体修剪和无基础的约束处理,影响答案的准确性和可信度。
- 本文提出关系中心探索范式,利用关系而非实体作为搜索单元,避免了不可靠的实体修剪,并提出组合关系链(CCoR)框架。
- 实验结果显示,CCoR在四个KGQA基准上相较于强基线在准确性、可信度和效率上均有显著提升,尤其在复杂查询上表现更为突出。
📝 摘要(中文)
知识图谱问答(KGQA)是评估知识图谱增强的大型语言模型(LLMs)的关键任务,尤其是需要多跳推理的复杂KGQA尤为具有挑战性。解决复杂查询涉及两个相互关联的阶段:候选检索和约束处理。现有方法在候选检索中依赖于实体中心探索,而约束处理则依赖于LLM的内部知识,导致不可靠的实体修剪和无基础的约束处理。为了解决这些问题,本文提出了一种关系中心探索范式,并基于此提出了组合关系链(CCoR)框架,利用两个关系链在KG中对两个阶段进行基础性支撑。实验结果表明,CCoR在四个KGQA基准上相较于强基线在准确性、可信度和效率上均有显著提升,尤其在复杂查询上表现更为突出。
🔬 方法详解
问题定义:本文旨在解决复杂知识图谱问答中的候选检索和约束处理问题。现有方法依赖于实体中心探索,导致实体修剪不可靠和约束处理无基础,最终影响答案的准确性和可信度。
核心思路:论文提出了一种关系中心探索的范式,利用关系作为搜索单元,避免了实体修剪带来的信息丢失。同时,提出组合关系链(CCoR)框架,确保候选检索和约束处理都基于知识图谱进行。
技术框架:CCoR框架包括两个主要模块:主链用于候选检索,约束链用于通过显式的知识图谱探索验证查询约束。整个流程通过关系链的组合实现对KG的有效利用。
关键创新:最重要的创新在于关系中心探索范式的提出,使得候选检索和约束处理都能在知识图谱的基础上进行,避免了现有方法中对实体的依赖和潜在的错误。
关键设计:在框架设计中,采用了关系链的组合方式,确保信息的完整性和准确性。具体的参数设置和损失函数设计未在摘要中详细说明,需参考论文的具体内容。
🖼️ 关键图片
📊 实验亮点
实验结果表明,CCoR在四个KGQA基准上相较于强基线在准确性上提升了X%,在可信度和效率上也有显著改善,尤其在复杂查询上,表现出更为明显的优势,验证了该方法的有效性。
🎯 应用场景
该研究的潜在应用领域包括智能问答系统、信息检索和知识管理等。通过提高知识图谱问答的准确性和可信度,能够为用户提供更可靠的信息检索服务,提升人机交互的质量。未来,该方法可能在更广泛的自然语言处理任务中得到应用,推动KGQA技术的发展。
📄 摘要(原文)
Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-hop reasoning is especially challenging. Solving a complex query involves two coupled phases: candidate retrieval, which locates answer candidates over the KG, and constraint handling, which filters these candidates against the query constraints. Faithful reasoning requires grounding both phases in the KG. However, existing agent-based methods ground candidate retrieval through entity-centric exploration, while leaving constraint handling to the LLM's internal knowledge, which leads to two critical limitations. (1) Unreliable entity pruning: entity-centric exploration uses entities as search units and must prune them to a fixed-size subset at each hop. Because entity information in KGs is often incomplete and a fixed-size subset cannot retain all valid entities, such pruning inevitably drops valid entities and ultimately leads to wrong answers. (2) Ungrounded constraint handling: query constraints are resolved from the LLM's internal knowledge rather than the KG, leaving the final answers unverifiable and prone to hallucination. To address these limitations, this paper introduces a relation-centric exploration paradigm, which uses relations rather than entities as search units and thus avoids unreliable entity pruning. Built on this paradigm, this paper proposes Compositional Chain-of-Relations (CCoR), a simple and effective framework that grounds both phases in the KG with two relation chains: a main chain for candidate retrieval and a constraint chain that verifies query constraints through explicit KG exploration. Experiments on four KGQA benchmarks show that CCoR consistently improves accuracy, faithfulness, and efficiency over strong baselines, with more pronounced gains on complex queries.