APA (7th ed.) Citation

Eshuijs, L., Wang, S., & Fokkens, A. (2026). Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design.

Chicago Style (17th ed.) Citation

Eshuijs, Leon, Shihan Wang, and Antske Fokkens. Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design. 2026.

MLA (9th ed.) Citation

Eshuijs, Leon, et al. Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design. 2026.