Zobrazeno 1 - 10
of 264
pro vyhledávání: '"Qiu Tianyi"'
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs a
Externí odkaz:
http://arxiv.org/abs/2406.20087
Autor:
Ji, Jiaming, Hong, Donghai, Zhang, Borong, Chen, Boyuan, Dai, Josef, Zheng, Boren, Qiu, Tianyi, Li, Boxun, Yang, Yaodong
In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for quest
Externí odkaz:
http://arxiv.org/abs/2406.15513
Autor:
Ji, Jiaming, Wang, Kaile, Qiu, Tianyi, Chen, Boyuan, Zhou, Jiayi, Li, Changye, Lou, Hantao, Yang, Yaodong
Large language models (LLMs) may exhibit undesirable behaviors. Recent efforts have focused on aligning these models to prevent harmful generation. Despite these efforts, studies have shown that even a well-conducted alignment process can be easily c
Externí odkaz:
http://arxiv.org/abs/2406.06144
Autor:
Qiu, Tianyi, Zeng, Fanzhi, Ji, Jiaming, Yan, Dong, Wang, Kaile, Zhou, Jiayi, Han, Yang, Dai, Josef, Pan, Xuehai, Yang, Yaodong
Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been systematically c
Externí odkaz:
http://arxiv.org/abs/2402.10184
Autor:
Ji, Jiaming, Chen, Boyuan, Lou, Hantao, Hong, Donghai, Zhang, Borong, Pan, Xuehai, Dai, Juntao, Qiu, Tianyi, Yang, Yaodong
With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current alignment me
Externí odkaz:
http://arxiv.org/abs/2402.02416
Autor:
Ji, Jiaming, Qiu, Tianyi, Chen, Boyuan, Zhang, Borong, Lou, Hantao, Wang, Kaile, Duan, Yawen, He, Zhonghao, Zhou, Jiayi, Zhang, Zhaowei, Zeng, Fanzhi, Ng, Kwan Yee, Dai, Juntao, Pan, Xuehai, O'Gara, Aidan, Lei, Yingshan, Xu, Hua, Tse, Brian, Fu, Jie, McAleer, Stephen, Yang, Yaodong, Wang, Yizhou, Zhu, Song-Chun, Guo, Yike, Gao, Wen
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve
Externí odkaz:
http://arxiv.org/abs/2310.19852
Autor:
Huang, Fengyu, Chen, Li, Yang, Xing, Jeyakumar, Paramsothy, Wang, Zhe, Sun, Shiyong, Qiu, Tianyi, Zeng, Yi, Chen, Jing, Huang, Min, Wang, Hailong, Fang, Linchuan
Publikováno v:
In Journal of Hazardous Materials 15 September 2024 477
Autor:
Huang, Fengyu, Chen, Li, Zhou, Ying, Huang, Jingqiu, Wu, Fang, Hu, Qing, Chang, Nan, Qiu, Tianyi, Zeng, Yi, He, Haoran, White, Jason C., Yang, Wenchao, Fang, Linchuan
Publikováno v:
In Journal of Hazardous Materials 5 September 2024 476
Autor:
Chen, Li, Yang, Xing, Huang, Fengyu, Zhu, Xiaozhen, Wang, Zhe, Sun, Shiyong, Dong, Faqin, Qiu, Tianyi, Zeng, Yi, Fang, Linchuan
Publikováno v:
In Environmental Pollution 1 September 2024 356
Autor:
Qiu, Tianyi1,2,3 (AUTHOR), Peñuelas, Josep4,5 (AUTHOR), Chen, Yinglong1,2,6 (AUTHOR), Sardans, Jordi4,5 (AUTHOR), Yu, Jialuo7 (AUTHOR), Xu, Zhiyuan1,2 (AUTHOR), Cui, Qingliang8 (AUTHOR), Liu, Ji9 (AUTHOR), Cui, Yongxing10 (AUTHOR), Zhao, Shuling8 (AUTHOR), Chen, Jing11 (AUTHOR), Wang, Yunqiang12 (AUTHOR), Fang, Linchuan1,3,8,12 (AUTHOR) flinc629@hotmail.com
Publikováno v:
iMeta. Jun2024, Vol. 3 Issue 3, p1-19. 19p.