Style de citation APA (7e éd.)

Liu, S., Chen, X., Urcelay, B. M., & Croce, F. (2026). Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders.

Style de citation Chicago (17e éd.)

Liu, Shunchang, Xin Chen, Belen Martin Urcelay, et Francesco Croce. Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders. 2026.

Style de citation MLA (9e éd.)

Liu, Shunchang, et al. Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders. 2026.