大模型智能体能力对齐

Aligning Agents to Follow Human ValuesTao GuiFudan University2024年6月YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP20242Fudan NLP LabWhere Is the Attention?Zhao, Wayne Xin, et al. "A survey of large language models." arXiv preprint arXiv:2303.18223 (2023).YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP20243Fudan NLP LabWhere Is the Attention?Achiam, Josh, et al. "Gpt-4 technical report." arXiv preprint arXiv:2303.08774 (2023).Ganguli, Deep, et al. "Predictability and surprise in large generative models." Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency. 2022.YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP2024YSSNLP20244Fudan NLP LabExciting and Perilous Journey toward AGISelf-preservationSpecific versus General Principles for Constitutional AI —— AnthropicThe exciting, perilous journey toward AGI —— Ilya SutskeverSelf-identityYSSNLP2024YSSNLP202