Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Chern, Steffi"'
Autor:
Chern, Steffi, Hu, Zhulin, Yang, Yuqing, Chern, Ethan, Guo, Yuan, Jin, Jiahe, Wang, Binjie, Liu, Pengfei
Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has received relatively less attention. Dishonest behaviors in LLMs, such as sp
Externí odkaz:
http://arxiv.org/abs/2406.13261
Autor:
Huang, Zhen, Wang, Zengzhi, Xia, Shijie, Li, Xuefeng, Zou, Haoyang, Xu, Ruijie, Fan, Run-Ze, Ye, Lyumanshan, Chern, Ethan, Ye, Yixin, Zhang, Yikai, Yang, Yuqing, Wu, Ting, Wang, Binjie, Sun, Shichao, Xiao, Yang, Li, Yiyuan, Zhou, Fan, Chern, Steffi, Qin, Yiwei, Ma, Yan, Su, Jiadi, Liu, Yixiu, Zheng, Yuxiang, Zhang, Shaoting, Lin, Dahua, Qiao, Yu, Liu, Pengfei
The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and s
Externí odkaz:
http://arxiv.org/abs/2406.12753
Despite the utility of Large Language Models (LLMs) across a wide range of tasks and scenarios, developing a method for reliably evaluating LLMs across varied contexts continues to be challenging. Modern evaluation approaches often use LLMs to assess
Externí odkaz:
http://arxiv.org/abs/2401.16788
While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve the general
Externí odkaz:
http://arxiv.org/abs/2401.05998
Autor:
Xu, Chunpu, Chern, Steffi, Chern, Ethan, Zhang, Ge, Wang, Zekun, Liu, Ruibo, Li, Jing, Fu, Jie, Liu, Pengfei
In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised fine-tuning,
Externí odkaz:
http://arxiv.org/abs/2312.15907
Autor:
Chern, I-Chun, Chern, Steffi, Chen, Shiqi, Yuan, Weizhe, Feng, Kehua, Zhou, Chunting, He, Junxian, Neubig, Graham, Liu, Pengfei
The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of tasks now face an increasing
Externí odkaz:
http://arxiv.org/abs/2307.13528
Autor:
Fromm, Davida1 fromm@andrew.cmu.edu, Chern, Steffi2, Geng, Zihan2, Kim, Mason2, Greenhouse, Joel2, MacWhinney, Brian1
Publikováno v:
Journal of Speech, Language & Hearing Research. Jul2024, Vol. 67, p2333-2342. 10p.