Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lv, Qitan"'
Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a promising
Externí odkaz:
http://arxiv.org/abs/2410.15116
Knowledge graphs (KGs) play a pivotal role in knowledge-intensive tasks across specialized domains, where the acquisition of precise and dependable knowledge is crucial. However, existing KG construction methods heavily rely on human intervention to
Externí odkaz:
http://arxiv.org/abs/2410.02811
Speculative decoding (SD), where an extra draft model is employed to provide multiple \textit{draft} tokens first and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However, exi
Externí odkaz:
http://arxiv.org/abs/2408.11850
Publikováno v:
Advances in Neural Information Processing Systems 36 (2024)
Inductive relation prediction (IRP) -- where entities can be different during training and inference -- has shown great power for completing evolving knowledge graphs. Existing works mainly focus on using graph neural networks (GNNs) to learn the rep
Externí odkaz:
http://arxiv.org/abs/2408.07088
Autor:
Wang, Jie, Chen, Hanzhu, Lv, Qitan, Shi, Zhihao, Chen, Jiajun, He, Huarui, Xie, Hongtao, Lian, Defu, Chen, Enhong, Wu, Feng
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on modeling gra
Externí odkaz:
http://arxiv.org/abs/2309.11528
Publikováno v:
Proceedings of SPIE; August 2022, Vol. 12306 Issue: 1 p123061H-123061H-8, 1107558p
Publikováno v:
Proceedings of SPIE; 10/1/2022, Vol. 12306, p123061H-123061H-8, 1p