Temporal Knowledge Graph Question Answering via Sub-Question Decomposition and Cross-Checking

Temporal Knowledge Graph Question Answering (TKGQA) requires precise alignment between natural language questions and temporally structured knowledge. While Large Language Models (LLMs) have shown promise in complex reasoning tasks, they often struggle with ambiguous temporal cues, resulting in hallucinations and limited robustness. To address these issues, we propose DeCompKGQA, a two-stage framework that leverages sub-question decomposition and a dedicated cross-checking module for iterative temporal reasoning. In the first stage, the input question is decomposed into a temporally constrained sub-question, enabling finer control over temporal conditions and logical dependencies while reducing ambiguity. In the second stage, the sub-question guides the selection of executable query templates for candidate retrieval, after which a cross-checking module compares the retrieved candidates against the outputs of an embedding-based TKGQA model on the same sub-question to determine the intermediate answer. This hybrid approach aligns the implicit reasoning capabilities of LLMs with explicit temporal facts, improving robustness and mitigating hallucinations. Experimental results on multiple benchmark datasets demonstrate that DeCompKGQA consistently outperforms strong baselines, achieving state-of-the-art performance on complex multi-hop temporal queries. Code is available at: https://github.com/lijh01/DeCompKGQA.