用引导图提升大模型在知识密集任务中的探索效率与准确性
Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs
- 引入中间引导图抽象目标知识结构，融合语义上下文
- 相比当前方法，复杂任务准确率提升15.6%，推理速度加快2.3倍
- 适合需精准知识检索的智能客服、医疗问答等场景
尽管大型语言模型具备强大语言能力，但其对静态知识的依赖和推理过程的不透明性限制了其在知识密集型任务中的表现。知识图谱虽具潜力，但现有探索方法存在根本权衡：基于问题的路径导致粒度不匹配引发冗余探索，基于线索的方法难以有效利用上下文信息应对复杂场景。为此，我们提出指导图引导的知识探索框架（GG Explore），引入中间引导图以连接非结构化查询与结构化知识检索。该引导图通过抽象目标知识结构并保留更广义语义上下文，定义了可检索空间，实现精确高效探索。在此基础上，我们构建：(1) 结构对齐机制，无需大模型开销即可过滤不兼容候选；(2) 上下文感知剪枝，通过图约束强化语义一致性。大量实验表明，本方法在复杂任务中显著优于最先进水平，效率提升2.3倍，准确率提高15.6%，且在小型语言模型上仍保持高性能，展现实际应用价值。
原文摘要 · Abstract (English)
While Large Language Models (LLMs) exhibit strong linguistic capabilities, their reliance on static knowledge and opaque reasoning processes limits their performance in knowledge intensive tasks. Knowledge graphs (KGs) offer a promising solution, but current exploration methods face a fundamental trade off: question guided approaches incur redundant exploration due to granularity mismatches, while clue guided methods fail to effectively leverage contextual information for complex scenarios. To address these limitations, we propose Guidance Graph guided Knowledge Exploration (GG Explore), a novel framework that introduces an intermediate Guidance Graph to bridge unstructured queries and structured knowledge retrieval. The Guidance Graph defines the retrieval space by abstracting the target knowledge' s structure while preserving broader semantic context, enabling precise and efficient exploration. Building upon the Guidance Graph, we develop: (1) Structural Alignment that filters incompatible candidates without LLM overhead, and (2) Context Aware Pruning that enforces semantic consistency with graph constraints. Extensive experiments show our method achieves superior efficiency and outperforms SOTA, especially on complex tasks, while maintaining strong performance with smaller LLMs, demonstrating practical value.
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。