Roger, Fabien

Alignment faking in large language models

Greenblatt, R., Denison, C., Wright, B., Roger, F., MacDiarmid, M., Marks, S., Treutlein, J., Belonax, T., Chen, J., Duvenaud, D., et al. (2024) · arXiv

Ethics and Social Impacts of AIAdversarial Robustness in Machine Learning

Cited by 30

Reasoning Models Don't Always Say What They Think

Chen, Y., Benton, J., Radhakrishnan, A., Uesato, J., Denison, C., Schulman, J., Somani, A., Hase, P., Wagner, M., Roger, F., et al. (2025) · arXiv

Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AI

Cited by 18

Auditing language models for hidden objectives

Marks, S., Treutlein, J., Bricken, T., Lindsey, J., Marcus, J., Mishra-Sharma, S., Ziegler, D., Ameisen, E., Batson, J., Belonax, T., et al. (2025) · arXiv

Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AI

Cited by 4

AI Control: Improving Safety Despite Intentional Subversion

Greenblatt, R., Shlegeris, B., Sachan, K., & Roger, F. (2023) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 3

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

Wichers, N., Ebtekar, A., Azarbal, A., Gillioz, V., Ye, C., Ryd, E., Rathi, N., Sleight, H., Mallen, A., Roger, F., et al. (2025) · arXiv

Adversarial Robustness in Machine LearningTopic Modeling

Cited by 0