机构
*
Lyles School of Civil and Construction Engineering, Purdue University(普渡大学莱尔斯土木与建筑工程学院)
;
Department of Civil and Environmental Engineering, University of Wisconsin-Madison(威斯康星大学麦迪逊分校土木与环境工程系)
;
Google(谷歌)
Resource Rational Contractualism Should Guide AI Alignment
资源理性契约主义应指导AI对齐
Sydney Levine, Matija Franklin, Tan Zhi-Xuan, Secil Yanik Guyot, Lionel Wong, Daniel Kilov, Yejin Choi, Joshua B. Tenenbaum, Noah Goodman, Seth Lazar, Iason Gabriel
机构
*
Harvard(哈佛大学)
;
MIT(麻省理工学院)
;
Google Deepmind(谷歌DeepMind)
;
Australian National University(澳大利亚国立大学)
;
Stanford Psychology Department(斯坦福心理学系)
;
Stanford(斯坦福大学)
;
Computer Science Department(计算机科学系)
机构
*
Shanghai Innovation Institute(上海创新研究院)
;
Nankai University(南开大学)
;
East China Normal University(华东师范大学)
;
AI for Science Institute, Beijing(北京人工智能科学研究院)
;
Peking University(北京大学)
;
DP Technology(DP技术公司)
;
Shanghai Jiao Tong University(上海交通大学)
;
National Key Laboratory of Advanced Micro and Nano Manufacture Technology, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai 200240, China(上海交通大学国家先进微纳米制造技术重点实验室,集成电路学院,上海200240,中国)
Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
提示是否保证安全?通过子空间干预减轻大语言模型生成中的毒性
Himanshu Singh, Ziwei Xu, A. V. Subramanyam, Mohan Kankanhalli
机构
*
Department of Computer Science(计算机科学系)
;
School of Computing, National University of Singapore(新加坡国立大学计算机学院)
;
Department of Electronics and Communications Engineering(电子与通信工程系)