通过拆解问题动态构建知识图谱，提升复杂问答的推理能力。
SUBQRAG: Sub-Question Driven Dynamic Graph RAG
- 将复杂问题分解为可验证的子问题链，逐层推理。
- 在图谱不足时实时从文档提取新三元组，提升证据完整性。
- 适合需要深度推理的多跳问答场景，如学术或医疗问答。
图谱增强生成（Graph RAG）通过构建知识图谱（KG）连接大规模文档中的零散事实，但在处理复杂多跳问答（QA）时，其全局视角常缺乏深层结构化推理能力，导致证据不全和错误累积。为此，我们提出子问题驱动的动态图谱增强框架SubQRAG。该框架将复杂问题分解为有序的可验证子问题链，对每个子问题从图谱中检索相关三元组。当现有图谱信息不足时，系统实时从源文档中提取新三元组并动态扩展图谱。所有推理过程中使用的三元组被聚合至“图谱记忆”中，形成结构化、可追溯的证据路径，用于最终答案生成。在三个多跳问答基准上的实验表明，SubQRAG在准确率上实现持续且显著的提升，尤其在精确匹配（Exact Match）指标上表现突出。
原文摘要 · Abstract (English)
Graph Retrieval-Augmented Generation (Graph RAG) effectively builds a knowledge graph (KG) to connect disparate facts across a large document corpus. However, this broad-view approach often lacks the deep structured reasoning needed for complex multi-hop question answering (QA), leading to incomplete evidence and error accumulation. To address these limitations, we propose SubQRAG, a sub-question-driven framework that enhances reasoning depth. SubQRAG decomposes a complex question into an ordered chain of verifiable sub-questions. For each sub-question, it retrieves relevant triples from the graph. When the existing graph is insufficient, the system dynamically expands it by extracting new triples from source documents in real time. All triples used in the reasoning process are aggregated into a "graph memory," forming a structured and traceable evidence path for final answer generation. Experiments on three multi-hop QA benchmarks demonstrate that SubQRAG achieves consistent and significant improvements, especially in Exact Match scores.
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。