用小模型找路径，大模型仅在必要时修复，提升问答准确率且省计算资源。
RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
- 小模型生成推理路径，大模型只在需要时介入修复。
- 平均每个问题仅需1.15次LLM调用，F1提升3.57点。
- 支持隐含约束过滤，适合对精度要求高的知识问答场景。
知识图谱问答（KGQA）通过将大模型推理锚定在结构化、可验证的知识图谱中，有效缓解了大模型幻觉问题。现有方法分为两类：基于检索的方案采用小型专用模型，高效但常产生不可达路径并忽略隐含约束；基于代理的方案使用大型通用模型，虽具更强结构化推理能力，但成本过高。本文提出RouterKGQA框架，实现专用与通用模型协同：专用模型生成推理路径，通用模型仅在必要时进行图谱引导修复，显著提升性能且代价极低。我们还为专用模型引入约束感知的答案过滤机制，减少冗余结果；设计更高效的通用代理工作流，进一步降低推理开销。实验表明，RouterKGQA在多个基准上平均F1提升3.57点，Hits@1提升0.49点，每问题平均仅需1.15次LLM调用。代码与模型已开源。
原文摘要 · Abstract (English)
Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized--general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 average LLM calls per question. Codes and models are available at https://github.com/Oldcircle/RouterKGQA.
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。