RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
This work addresses the challenge of balancing efficiency and accuracy in KGQA for mitigating LLM hallucination, representing an incremental improvement over existing paradigms.
The paper tackles the problem of knowledge graph question answering by proposing RouterKGQA, a framework that combines specialized and general models to improve performance while reducing costs, achieving a 3.57-point F1 and 0.49-point Hits@1 gain over previous methods with only 1.15 average LLM calls per question.
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.