Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Kai, Jushi"'
Autor:
Tang, Yihong, Wang, Zhaokai, Qu, Ao, Yan, Yihao, Wu, Zhaofeng, Zhuang, Dingyi, Kai, Jushi, Hou, Kebing, Guo, Xiaotong, Zhao, Jinhua, Zhao, Zhan, Ma, Wei
Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Plann
Externí odkaz:
http://arxiv.org/abs/2402.07204
Large language models (LLMs) demonstrate great performance in text generation. However, LLMs are still suffering from hallucinations. In this work, we propose an inference-time method, Self-Highlighted Hesitation (SH2), to help LLMs decode more truth
Externí odkaz:
http://arxiv.org/abs/2401.05930
Autor:
Hou, Shengyuan, Kai, Jushi, Xue, Haotian, Zhu, Bingyu, Yuan, Bo, Huang, Longtao, Wang, Xinbing, Lin, Zhouhan
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information from data
Externí odkaz:
http://arxiv.org/abs/2210.11759