English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

The rapid advancements in large language models (LLMs) have ignited interestin the temporal knowledge graph (tKG) domain, where conventionalembedding-based and rule-based methods dominate. The question remains open ofwhether pre-trained LLMs can understand structured temporal relational data andreplace them as the foundation model for temporal relational forecasting.Therefore, we bring temporal knowledge forecasting into the generative setting.However, challenges occur in the huge chasms between complex temporal graphdata structure and sequential natural expressions LLMs can handle, and betweenthe enormous data sizes of tKGs and heavy computation costs of finetuning LLMs.To address these challenges, we propose a novel retrieval-augmented generationframework named GenTKG combining a temporal logical rule-based retrievalstrategy and few-shot parameter-efficient instruction tuning to solve the abovechallenges, respectively. Extensive experiments have shown that GenTKGoutperforms conventional methods of temporal relational forecasting with lowcomputation resources using extremely limited training data as few as 16samples. GenTKG also highlights remarkable cross-domain generalizability withoutperforming performance on unseen datasets without re-training, and in-domaingeneralizability regardless of time split in the same dataset. Our work revealsthe huge potential of LLMs in the tKG domain and opens a new frontier forgenerative forecasting on tKGs. Code and data are released here:https://github.com/mayhugotong/GenTKG.

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models