@article{elicitingsecretknowledgefromlanguagemode, title = {Eliciting Secret Knowledge from Language Models}, author = {Bartosz CywiƄski and Emil Ryd and Rowan Wang and Senthooran Rajamanoharan and Neel Nanda and Arthur Conmy and Samuel Marks}, year = {2025}, eprint = {2510.01070}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.01070}, }