Language Models Learn to Mislead Humans via RLHF

Documenti analoghi

• Learning Task Decomposition to Assist Humans in Competitive Programming
  di: Wen, Jiaxin, et al.
  Pubblicazione: (2024)
• Explaining Datasets in Words: Statistical Models with Natural Language Parameters
  di: Zhong, Ruiqi, et al.
  Pubblicazione: (2024)
• Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
  di: Wen, Jiaxin, et al.
  Pubblicazione: (2024)
• How do Language Models Bind Entities in Context?
  di: Feng, Jiahai, et al.
  Pubblicazione: (2023)
• ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
  di: Hou, Zhenyu, et al.
  Pubblicazione: (2024)