@article{lookinginwardlanguagemodelscanlearn, title = {Looking Inward: Language Models Can Learn About Themselves by Introspection}, author = {Felix J Binder and James Chua and Tomek Korbak and Henry Sleight and John Hughes and Robert Long and Ethan Perez and Miles Turpin and Owain Evans}, year = {2024}, eprint = {2410.13787}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13787v1}, }