用规划引导图检索，提升半结构化知识库搜索效果
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
- 分三阶段：先规划检索路径，再融合文本与图信息，最后重排序
- 在三个基准上平均命中率从62.0提升至73.9，显著优于现有方法
- 适合需要精准检索的场景，如医疗、学术和商品搜索
半结构化知识库（SKBs）将文本文档嵌入实体与关系的类型化图中，支撑产品搜索、学术论文检索和精准医疗等应用。现有混合检索系统或仅用图进行查询扩展，或以全局权重混合文本与结构分支，或依赖微调的图遍历生成器。我们提出GRASP，一种三阶段SKB检索框架，统一了基于计划的图检索、基于计划的稠密检索融合，以及对融合候选结果的微调重排序。GRASP在三个STaRK基准上各项指标均大幅领先，平均命中率（Hit@1）从62.0提升至73.9。消融实验与敏感性分析进一步验证了GRASP的有效性与鲁棒性。
原文摘要 · Abstract (English)
Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval systems on SKBs either use the graph only for query expansion, mix textual and structural branches under a global weighting, or rely on fine-tuned graph-traversal generators. We present GRASP, a three-stage SKB retrieval framework unifying plan-based graph retrieval, plan-conditioned fusion with a dense retriever, and a fine-tuned reranker over the fused candidates. GRASP substantially advances the state of the art on every metric across the three STaRK benchmarks, lifting average Hit@1 from 62.0 to 73.9. Ablation and sensitivity studies further confirm the effectiveness and robustness of GRASP.
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。