arXiv:2506.13380cs.CLcs.IR2025-06

平衡知识图谱检索的内容与结构,提升大模型推理效果。

The Structure-Content Trade-off in Knowledge Graph Retrieval

  • 用混合检索函数控制主问题与子问题的重要性。
  • 子问题检索提升内容准确率,但图谱碎片化。
  • 主问题检索保持结构连贯性,但相关性下降。

大型语言模型(LLMs)越来越多地依赖知识图谱进行事实推理,但检索设计如何影响其性能仍不明确。我们研究了问题分解如何改变检索子图的内容与结构。通过使用一种混合检索函数,该函数可调节初始问题与子问题的重要性,我们发现基于子问题的检索能提高内容精度,但导致子图不连贯;而基于主问题的检索虽维持结构完整性,却降低了相关性。最优性能出现在两者之间,表明在知识图谱检索中平衡内容与结构是实现有效大模型推理的关键。

原文摘要 · Abstract (English)

Large Language Models (LLMs) increasingly rely on knowledge graphs for factual reasoning, yet how retrieval design shapes their performance remains unclear. We examine how question decomposition changes the retrieved subgraph's content and structure. Using a hybrid retrieval function that controls the importance of initial question and subquestions, we show that subquestion-based retrieval improves content precision, but yields disjoint subgraphs, while question-based retrieval maintains structure at the cost of relevance. Optimal performance arises between these extremes, revealing that balancing retrieval content and structure is key to effective LLM reasoning over structured knowledge.

知识图谱检索优化大模型推理

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。