发表机构
New York University Abu Dhabi（纽约大学阿布扎比分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对知识图谱不完整导致多跳问答推理路径断裂的问题，提出XoG框架，利用类型级统计和嵌入恢复缺失路径，LLM作语义选择器，在多个基准上优于可比方法并降低33%令牌消耗。
AI 中文摘要
大语言模型（LLMs）越来越多地与知识图谱（KGs）结合，以在结构化证据基础上进行推理。然而，大多数基于LLM的知识图谱问答（KGQA）方法依赖于遍历现有图边，当推理路径因缺失事实而中断时，这些方法变得不可靠。替代方案要求LLM生成缺失知识，但存在引入幻觉证据的风险。我们提出XoG（eXplore-on-Graph），一个面向不完整KG的多跳问答框架，它从学习到的图结构中恢复缺失的推理路径，而非依赖LLM的参数化知识。XoG结合类型级实体-关系统计来识别候选关系，并利用KG嵌入检索合理的缺失实体，同时将LLM用作语义选择器和推理器。这些机制被整合到一个迭代的规划-探索-推理过程中。在WebQSP、CWQ和基于Wikidata的BRINK基准上的实验表明，XoG在完整KG上保持竞争力，并在KG不完整条件下持续优于没有任务特定KGQA训练的可比方法。这些优势在多个LLM骨干网络上持续存在，表明仅靠更强的LLM并不能解决缺失图证据的问题。与紧密相关的基于规划的方法相比，XoG还将LLM的令牌消耗降低了高达33%。
英文摘要
Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based KGQA methods rely on traversing existing graph edges and become unreliable when reasoning paths are broken by missing facts. Alternatives that ask LLMs to generate missing knowledge risk introducing hallucinated evidence. We introduce XoG (eXplore-over-Graph), a framework for multi-hop question answering over incomplete KGs that recovers missing reasoning paths from learned graph structure rather than LLM parametric knowledge. XoG combines type-level entity-relation statistics to identify candidate relations with KG embeddings to retrieve plausible missing entities, using the LLM as a semantic selector and reasoner. These mechanisms are integrated into an iterative planning-exploration-reasoning process. Experiments on WebQSP, CWQ, and the Wikidata-based BRINK benchmark show that XoG remains competitive on complete KGs and consistently outperforms comparable methods without task-specific KGQA training under KG incompleteness. These gains persist across multiple LLM backbones, indicating that stronger LLMs alone do not resolve missing graph evidence. XoG also reduces LLM token consumption by up to 33% compared with a closely related planning-based approach.
