today local_bar

Gholamali Aminian

Researcher, Alan Turing Institute

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity

#510 · Gholamali Aminian, Amir R. Asadi, Idan Shenfeld, Youssef Mroueh

We provide theoretical analysis for forward and reverse KL-regularized RLHF under multiple reference models.