English

The benefits of query-based KGQA systems for complex and temporal questions in LLM era

Computation and Language 2025-07-17 v1 Machine Learning

Abstract

Large language models excel in question-answering (QA) yet still struggle with multi-hop reasoning and temporal questions. Query-based knowledge graph QA (KGQA) offers a modular alternative by generating executable queries instead of direct answers. We explore multi-stage query-based framework for WikiData QA, proposing multi-stage approach that enhances performance on challenging multi-hop and temporal benchmarks. Through generalization and rejection studies, we evaluate robustness across multi-hop and temporal QA datasets. Additionally, we introduce a novel entity linking and predicate matching method using CoT reasoning. Our results demonstrate the potential of query-based multi-stage KGQA framework for improving multi-hop and temporal QA with small language models. Code and data: https://github.com/ar2max/NLDB-KGQA-System

Keywords

Cite

@article{arxiv.2507.11954,
  title  = {The benefits of query-based KGQA systems for complex and temporal questions in LLM era},
  author = {Artem Alekseev and Mikhail Chaichuk and Miron Butko and Alexander Panchenko and Elena Tutubalina and Oleg Somov},
  journal= {arXiv preprint arXiv:2507.11954},
  year   = {2025}
}

Comments

15 pages, 3 figures, 7 tables