发表机构
Sun Yat-sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对现有基于LLM的KGQA方法存在的实体剪枝不可靠、约束处理无基础的局限，提出组合式关系链（CCoR）框架，以关系为中心探索实现更忠实的多跳KGQA，在多个基准上性能优于基线。
AI 中文摘要
知识图谱问答（KGQA）是评估结合知识图谱（KG）的大型语言模型（LLM）的关键任务，需要多跳推理的复杂KGQA尤其具有挑战性。解决复杂查询涉及两个耦合阶段：候选检索，即定位KG上的答案候选；以及约束处理，即根据查询约束筛选这些候选。忠实推理要求两个阶段都以KG为基础。然而，现有的基于智能体的方法通过以实体为中心的探索来实现候选检索，而将约束处理留给LLM的内部知识，这导致了两个关键局限：（1）不可靠的实体剪枝：以实体为中心的探索将实体作为搜索单元，且每一步必须将它们剪枝为固定大小的子集。由于KG中的实体信息通常不完整，固定大小的子集无法保留所有有效实体，因此这种剪枝不可避免地会丢弃有效实体，最终导致错误答案。（2）无基础的约束处理：查询约束是从LLM的内部知识中解析出来的，而非基于KG，这使得最终答案无法验证且容易产生幻觉。为解决这些局限，本文引入了以关系为中心的探索范式，该范式将关系而非实体作为搜索单元，从而避免了不可靠的实体剪枝。基于该范式，本文提出了组合式关系链（CCoR），这是一个简单有效的框架，通过两条关系链将两个阶段都建立在KG基础上：用于候选检索的主链，以及通过显式KG探索验证查询约束的约束链。在四个KGQA基准上的实验表明，与强大的基线相比，CCoR在准确性、忠实性和效率方面均有提升，且在复杂查询上的提升更为显著。
英文摘要
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.
