Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Ji, Hangyuan"'
Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model
Autor:
Hou, Xia, Li, Qifeng, Yang, Jian, Li, Tongliang, Chai, Linzheng, Wu, Xianjie, Ji, Hangyuan, Li, Zhoujun, Nie, Jixuan, Dun, Jingbo, Song, Wenfeng
Instruction tuning as an effective technique aligns the outputs of large language models (LLMs) with human preference. But how to generate the seasonal multi-turn dialogues from raw documents for instruction tuning still requires further exploration.
Externí odkaz:
http://arxiv.org/abs/2407.03040
Autor:
Ji, Hangyuan, Yang, Jian, Chai, Linzheng, Wei, Chaoren, Yang, Liqun, Duan, Yunlong, Wang, Yunli, Sun, Tianzhen, Guo, Hongcheng, Li, Tongliang, Ren, Changyu, Li, Zhoujun
To address the increasing complexity and frequency of cybersecurity incidents emphasized by the recent cybersecurity threat reports with over 10 billion instances, cyber threat intelligence (CTI) plays a critical role in the modern cybersecurity land
Externí odkaz:
http://arxiv.org/abs/2405.03446
Autor:
Zhang, Wei, Guo, Hongcheng, Yang, Jian, Zhang, Yi, Yan, Chaoran, Tian, Zhoujin, Ji, Hangyuan, Li, Zhoujun, Li, Tongliang, Zheng, Tieqiao, Chen, Chao, Liang, Yi, Shi, Xu, Zheng, Liangfan, Zhang, Bo
The escalating complexity of micro-services architecture in cloud-native technologies poses significant challenges for maintaining system stability and efficiency. To conduct root cause analysis (RCA) and resolution of alert events, we propose a pion
Externí odkaz:
http://arxiv.org/abs/2404.12135
Autor:
Zhu, Yinghao, Ren, Changyu, Xie, Shiyun, Liu, Shukai, Ji, Hangyuan, Wang, Zixiang, Sun, Tao, He, Long, Li, Zhoujun, Zhu, Xi, Pan, Chengwei
The integration of multimodal Electronic Health Records (EHR) data has significantly improved clinical predictive capabilities. Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to cli
Externí odkaz:
http://arxiv.org/abs/2402.07016