用递归思维让大模型更准地回答复杂时间知识图谱问题
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
- 通过递归分解问题，逐层求解并融合多路径答案
- 在多跳和复杂查询上Hits@1提升显著，优于现有方法
- 无需训练，适合需要高精度时序推理的研究者
当前的时间知识图谱问答方法主要关注隐式时间约束，难以处理更复杂的时序查询，且在分解框架中存在推理能力弱和错误传播问题。我们提出RTQA框架，通过递归思维增强对时序知识图谱的推理能力，无需训练即可实现。RTQA将问题递归分解为子问题，自底向上利用大语言模型与知识图谱信息求解，并通过多路径答案聚合提升容错性。该框架包含三个核心组件：时间问题分解器、递归求解器和答案聚合器。在MultiTQ和TimelineKGQA基准上的实验表明，其在“Multiple”和“Complex”类别中显著提升Hits@1性能，超越现有最先进方法。代码与数据已公开于https://github.com/zjukg/RTQA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。