@article{toobigtofoolresistingdeceptionin, title = {Too Big to Fool: Resisting Deception in Language Models}, author = {Mohammad Reza Samsami and Mats Leon Richter and Juan Rodriguez and Megh Thakkar and Sarath Chandar and Maxime Gasse}, year = {2024}, eprint = {2412.10558}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10558v1}, }