Enhancing Temporal Knowledge Graph Question Answering via Multi-level Temporal Knowledge Retrieval with Large Language Models

Abstract

Temporal Knowledge Graph Question Answering (TKG-QA) requires reasoning over time-evolving facts, yet existing approaches struggle to jointly capture temporal dependencies and semantic understanding. Traditional graph-based methods often miss semantic nuances, while LLM-based solutions lack temporal alignment, leading to inaccurate retrieval and incomplete reasoning. To address this gap, we propose a framework that bridges structured temporal modeling with the reasoning capacity of large language models. Our approach reconstructs temporal knowledge into semantically coherent text representations and employs a hybrid retrieval mechanism to ensure precise and temporally consistent evidence selection. Besides, we design an interpretable reasoning process that guides LLMs to effectively combine temporal structure with semantic inference. Experiments on CronQuestions and MultiTQ demonstrate significant gains, with improvements of 6.1% and 12.1% over the best baselines, confirming the advantage of unifying temporal knowledge modeling and language-based reasoning for TKG-QA.