Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
Jiapu Wang, Kai Sun, Linhao Luo, Wei Wei, Yongli Hu, Alan Wee-Chung Liew, Shirui Pan, Baocai Yin
Abstract
Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rule-based TKGRs struggle to effectively learn temporal rules that capture temporal patterns. Recently, Large Language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning. Consequently, the employment of LLMs for Temporal Knowledge Graph Reasoning (TKGR) has sparked increasing interest among researchers. Nonetheless, LLMs are known to function as black boxes, making it challenging to comprehend their reasoning process. Additionally, due to the resource-intensive nature of fine-tuning, promptly updating LLMs to integrate evolving knowledge within TKGs for reasoning is impractical. To address these challenges, in this paper, we propose a Large Language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on TKGs. Specifically, LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules. These rules unveil temporal patterns and facilitate interpretable reasoning. To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events. This ensures that the extracted rules always incorporate the most recent knowledge and better generalize to the predictions on future events. Experimental results show that without the need of fine-tuning, LLM-DA significantly improves the accuracy of reasoning over several common datasets, providing a robust framework for TKGR tasks.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
25 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning cites Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
- G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
Cited by top-tier papers25
- G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable RecommendationYuhan Li, Xinni Zhang, Linhao Luo, Heng Chang et al.WWW 2025 · 46 citations
- Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient TransformationHe Zhang, Bang Wu, Xiangwen Yang, Xingliang Yuan et al.WWW 2025 · 16 citations
- MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented GenerationWenlong Wu, Haofen Wang, Bohan Li, Peixuan Huang et al.ICDE 2025 · 16 citations
- Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language ModelsSiwei Zhang, Yun Xiong, Yateng Tang, Jiarong Xu et al.NeurIPS 2025 · 9 citations
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge GraphsKai Chen, Xin Song, Ye Wang, Liqun Gao et al.AAAI 2025 · 6 citations
Builds on23
- Time-LLM: Time Series Forecasting by Reprogramming Large Language ModelsMing Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu et al.ICLR 2024 · 915 citations
- Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
- Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge GraphsWoojeong Jin, Meng Qu, Xisen Jin, Xiang RenEMNLP 2020 · 353 citations
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation LearningZixuan Li, Xiaolong Jin, Wei Li, Saiping Guan et al.SIGIR 2021 · 345 citations
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation NetworksCunchao Zhu, Muhao Chen, Changjun Fan, Guangquan Cheng et al.AAAI 2021 · 343 citations
Related papers
- SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph ExtrapolationFu Zhang, Panfeng Zhang, Jingwei ChengEMNLP Findings 2025
- PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language ModelsYu Liu, Xixun Lin, Yanmin Shang, Yangxi Li et al.AAAI 2026 · 3 citations
- STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph ExtrapolationShuyuan Zhao, Wei Chen, Weijie Zhang, Xinrui Hou et al.ACL 2026
- TimeR⁴ : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question AnsweringXinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou et al.EMNLP 2024 · 11 citations
- Large Language Models Can Learn Temporal ReasoningSiheng Xiong, Ali Payani, Ramana Kompella, Faramarz FekriACL 2024
