Lermen, S., Dziemian, M., & Antolín, N. P. (2025). Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems.
Style de citation Chicago (17e éd.)Lermen, Simon, Mateusz Dziemian, et Natalia Pérez-Campanero Antolín. Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems. 2025.
Style de citation MLA (9e éd.)Lermen, Simon, et al. Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems. 2025.
Attention : ces citations peuvent ne pas être correctes à 100%.