让大模型在不完整知识图谱中也能精准推理。
Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
- 用大模型导航+嵌入相似度扩展，补全缺失关系
- 在多种构建方式的知识图谱上准确率提升5%至27%
- 自动分流简单查询，兼顾效率与深度推理
GraphRAG 被广泛用于将非结构化文本转化为图结构以支持多跳推理。然而，标准图算法依赖静态连接和显式边，在真实场景中常因知识图谱（KG）噪声大、稀疏或不完整而失效。为此，我们提出 INSES（智能导航与相似性增强搜索）框架，通过大模型引导的导航来剔除噪声并引导探索，结合基于嵌入的相似性扩展以恢复隐藏链接、弥合语义鸿沟。为应对图推理的计算开销，我们设计轻量级路由器：简单查询交由朴素 RAG 处理，复杂任务则移交 INSES，实现效率与推理深度的平衡。INSES 在多个基准测试中持续优于现有 SOTA 的 RAG 和 GraphRAG 方法。尤其在 MINE 基准上，针对不同构建方式（KGGEN、GraphRAG、OpenIE）生成的图，准确率分别提升 5%、10% 和 27%。
原文摘要 · Abstract (English)
GraphRAG is increasingly adopted for converting unstructured corpora into graph structures to enable multi-hop reasoning. However, standard graph algorithms rely heavily on static connectivity and explicit edges, often failing in real-world scenarios where knowledge graphs (KGs) are noisy, sparse, or incomplete. To address this limitation, we introduce INSES (Intelligent Navigation and Similarity Enhanced Search), a dynamic framework designed to reason beyond explicit edges. INSES couples LLM-guided navigation, which prunes noise and steers exploration, with embedding-based similarity expansion to recover hidden links and bridge semantic gaps. Recognizing the computational cost of graph reasoning, we complement INSES with a lightweight router that delegates simple queries to Naïve RAG and escalates complex cases to INSES, balancing efficiency with reasoning depth. INSES consistently outperforms SOTA RAG and GraphRAG baselines across multiple benchmarks. Notably, on the MINE benchmark, it demonstrates superior robustness across KGs constructed by varying methods (KGGEN, GraphRAG, OpenIE), improving accuracy by 5%, 10%, and 27%, respectively.
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。