.png){kind=icon}
.png){kind=icon}
Return
Structure-aware generative framework for temporal knowledge graph reasoning with historical evidence
.png){kind=icon}
PRE
AI
DOI：10.1007/s11280-026-01428-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Temporal knowledge graph reasoning (TKGR) aims to predict missing facts or infer future events based on historical information. Recently, language model (LM)-based approaches have shown promising results by incorporating textual representations of historical facts. However, existing LM-based methods still face two key limitations: they do not adequately capture structural dependencies in TKGs, and most approaches formulate reasoning as a discriminative task rather than leveraging the generative capability of modern large language models (LLMs). To address these limitations, we propose SAG, a Structure-Aware Generative framework for temporal knowledge graph reasoning with historical evidence. Specifically, SAG first constructs dual-view historical evidence to better capture structural dependencies in temporal knowledge graphs. The structural representations are then projected into the embedding space of a large language model as soft evidence tokens through a structure-text adapter, enabling the language model to jointly reason over structural evidence and textual query context. Finally, SAG formulates TKGR as an end-to-end generative task through instruction tuning, allowing the model to directly generate the missing entity. Extensive experiments on three widely used benchmarks demonstrate that SAG consistently outperforms strong baselines. In particular, compared with the strongest baseline, SAG achieves Hits@1 improvements of 6.45%, 2.78%, and 8.52% on ICEWS14, ICEWS18, and ICEWS05-15, respectively. Further analyses verify the effectiveness and robustness of the proposed framework.
Keywords:
Temporal knowledge graph reasoning
Large language models
Generative reasoning
Temporal structural dependencies
Journal
W
IF:
3.4
Papers:
49
Citations:
2.3K
View more organizations