用检索增强的推理框架，解决知识图谱中复杂逻辑查询难题
ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs
- 通过检索相关邻域数据，分步拆解复杂逻辑查询
- 在高复杂度和含否定的查询上准确率显著提升
- 适合需要严谨逻辑推理的知识图谱应用
在不完整知识图谱上回答一阶逻辑（FOL）查询极具挑战，尤其对于包含投影、交集、并集和否定的复杂查询结构。我们提出ROG，一种融合查询感知邻域检索与大语言模型链式思维推理的增强框架。ROG将多算子查询分解为一系列单算子子查询，并在每一步中使用紧凑且与查询相关的邻域证据进行锚定。中间答案集被缓存并在各步骤间复用，提升了深层推理链条的一致性。该设计有效降低误差累积，在复杂和含否定的查询上实现更稳健的推理。整体而言，ROG通过检索驱动的逐步推理替代学习型算子，为嵌入式逻辑推理提供了实用替代方案。在标准知识图谱推理基准上的实验表明，其性能持续优于强嵌入基线，尤其在高复杂度和否定密集型查询类型上提升最大。
原文摘要 · Abstract (English)
Answering first-order logic (FOL) queries over incomplete knowledge graphs (KGs) is difficult, especially for complex query structures that compose projection, intersection, union, and negation. We propose ROG, a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning. ROG decomposes a multi-operator query into a sequence of single-operator sub-queries and grounds each step in compact, query-relevant neighborhood evidence. Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains. This design reduces compounding errors and yields more robust inference on complex and negation-heavy queries. Overall, ROG provides a practical alternative to embedding-based logical reasoning by replacing learned operators with retrieval-grounded, step-wise inference. Experiments on standard KG reasoning benchmarks show consistent gains over strong embedding-based baselines, with the largest improvements on high-complexity and negation-heavy query types.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。