RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Bo, Deng, Hexuan, Liu, Xuebo, Zhang, Min
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917354844192768
author Yuan, Bo
Deng, Hexuan
Liu, Xuebo
Zhang, Min
author_facet Yuan, Bo
Deng, Hexuan
Liu, Xuebo
Zhang, Min
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20017
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
Yuan, Bo
Deng, Hexuan
Liu, Xuebo
Zhang, Min
Computation and Language
Databases
Information Retrieval
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.
title RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
topic Computation and Language
Databases
Information Retrieval
url https://arxiv.org/abs/2603.20017