JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Junlan, Meng, Fanyu, Long, Chong, Cong, Pengyu, Wang, Duqing, Zheng, Yan, Zhang, Yuyao, Gao, Xuanchang, Yuan, Ye, Ma, Yunfei, Ren, Zhijie, Yang, Fan, Wu, Na, Jin, Di, Deng, Chao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.17918