Barla, A., Nevali, E., Viano, L., & Cevher, V. (2026). Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution.
Chicago Style (17th ed.) CitationBarla, Adam, Emanuele Nevali, Luca Viano, and Volkan Cevher. Provably Avoiding Over-optimization in Direct Preference Optimization Without Knowing the Data Distribution. 2026.
MLA (9th ed.) CitationBarla, Adam, et al. Provably Avoiding Over-optimization in Direct Preference Optimization Without Knowing the Data Distribution. 2026.
Warning: These citations may not always be 100% accurate.