RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gong, Zhaoyan, Li, Juan, Liu, Zhiqiang, Liang, Lei, Chen, Huajun, Zhang, Wen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909770507616256
author Gong, Zhaoyan
Li, Juan
Liu, Zhiqiang
Liang, Lei
Chen, Huajun
Zhang, Wen
author_facet Gong, Zhaoyan
Li, Juan
Liu, Zhiqiang
Liang, Lei
Chen, Huajun
Zhang, Wen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03995
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Gong, Zhaoyan
Li, Juan
Liu, Zhiqiang
Liang, Lei
Chen, Huajun
Zhang, Wen
Computation and Language
Artificial Intelligence
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.
title RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.03995