通过推理时计算扩展，提升大模型在知识图谱上的多跳问答能力
Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
- 推理时动态扩展计算，结合链式思考与并行采样路径
- 在GRBench上多跳问答准确率显著优于传统GraphRAG
- 无需修改模型架构，适合各类基于LLM的知识推理任务
大型语言模型在语言理解与生成方面表现优异，但在需要大量知识的推理任务中仍表现不足，主要因缺乏对结构化上下文和多跳信息的访问。检索增强生成（RAG）部分缓解了这一问题，但传统RAG与GraphRAG方法难以捕捉知识图谱中节点间的关联结构。我们提出推理时缩放图RAG（Inference-Scaled GraphRAG），通过推理时计算扩展来增强基于大模型的图推理能力。该方法结合顺序扩展与深度链式思考图遍历，以及并行扩展与采样路径的多数投票机制，在交错推理-执行循环中实现高效推理。在GRBench基准测试中，该方法显著提升了多跳问答性能，相比传统GraphRAG及先前图遍历基线取得明显优势。结果表明，推理时缩放是一种实用且架构无关的结构化知识推理解决方案。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have achieved impressive capabilities in language understanding and generation, yet they continue to underperform on knowledge-intensive reasoning tasks due to limited access to structured context and multi-hop information. Retrieval-Augmented Generation (RAG) partially mitigates this by grounding generation in retrieved context, but conventional RAG and GraphRAG methods often fail to capture relational structure across nodes in knowledge graphs. We introduce Inference-Scaled GraphRAG, a novel framework that enhances LLM-based graph reasoning by applying inference-time compute scaling. Our method combines sequential scaling with deep chain-of-thought graph traversal, and parallel scaling with majority voting over sampled trajectories within an interleaved reasoning-execution loop. Experiments on the GRBench benchmark demonstrate that our approach significantly improves multi-hop question answering performance, achieving substantial gains over both traditional GraphRAG and prior graph traversal baselines. These findings suggest that inference-time scaling is a practical and architecture-agnostic solution for structured knowledge reasoning with LLMs
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。