RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
This addresses limitations in temporal knowledge graph question answering for applications requiring complex reasoning, representing an incremental advance with novel method integration.
The paper tackles the problem of answering complex temporal queries on knowledge graphs by proposing RTQA, a framework that recursively decomposes questions and uses large language models to solve sub-problems, achieving significant Hits@1 improvements on benchmarks like MultiTQ and TimelineKGQA.
Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves them bottom-up using LLMs and TKG knowledge, and employs multi-path answer aggregation to improve fault tolerance. RTQA consists of three core components: the Temporal Question Decomposer, the Recursive Solver, and the Answer Aggregator. Experiments on MultiTQ and TimelineKGQA benchmarks demonstrate significant Hits@1 improvements in "Multiple" and "Complex" categories, outperforming state-of-the-art methods. Our code and data are available at https://github.com/zjukg/RTQA.