Tell me about yourself: LLMs are aware of their learned behaviors

Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua, Owain Evans. Tell me about yourself: LLMs are aware of their learned behaviors. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]

Authors

Jan Betley

This author has not been identified. Look up 'Jan Betley' in Google

Xuchan Bao

This author has not been identified. Look up 'Xuchan Bao' in Google

Martín Soto

This author has not been identified. Look up 'Martín Soto' in Google

Anna Sztyber-Betley

This author has not been identified. Look up 'Anna Sztyber-Betley' in Google

James Chua

This author has not been identified. Look up 'James Chua' in Google

Owain Evans

This author has not been identified. Look up 'Owain Evans' in Google