LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (11) · 11481-11489
DOI: 10.1609/aaai.v39i11.33249 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Kai Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
Among various temporal knowledge graph (TKG) extrapolation methods, rule-based approaches stand out for their explicit rules and transparent reasoning paths. However, the vast search space for rule extraction poses a challenge in identifying high-quality logic rules. To navigate this challenge, we explore the use of generation models to generate new rules, thereby enriching our rule base and enhancing our reasoning capabilities. In this paper, we introduce LLM-DR, an innovative rule-based method for TKG extrapolation, which harnesses diffusion models to generate rules that are consistent with the distribution of the source data, while also amalgamating the rich semantic insights of Large Language Models (LLMs). Specifically, our LLM-DR generates semantically relevant and high-quality rules, employing conditional diffusion models in a classifier-free guidance fashion and refining them with LLM-based constraints. To assess rule efficacy, we meticulously design a coarse-to-fine evaluation strategy that initiates with coarse-grained filtering to eliminate less plausible rules and proceeds with fine-grained scoring to quantify the reliability of the retained. Extensive experiments demonstrate the promising capacity of our LLM-DR.
Zitieren
APA
Chen, K., Song, X., Wang, Y., Gao, L., Li, A., Zhao, X., Zhou, B., & Xie, Y. (2025). LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 39(11), 11481-11489. https://doi.org/10.1609/aaai.v39i11.33249
Vancouver
Chen K, Song X, Wang Y, Gao L, Li A, Zhao X, et al. LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(11):11481-11489. doi:10.1609/aaai.v39i11.33249
BibTeX
@article{Chen2025,
author = {Chen, Kai and Song, Xin and Wang, Ye and Gao, Liqun and Li, Aiping and Zhao, Xiaojuan and Zhou, Bin and Xie, Yalong},
title = {LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {11},
pages = {11481--11489},
doi = {10.1609/aaai.v39i11.33249}
}
EUVIMED