AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework

Kihyun Kim, Jiawei Zhang, Asuman E. Ozdaglar, Pablo A. Parrilo

ICLR 2026 · Reinforcement learning › RL from feedback · approach: Reward modeling versus direct optimization · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase softmax beta in F^beta (ablation)F^beta · MovieLens tabularwin rate vs uniform: 0.5987 -> 0.7784Improved
increase softmax beta in F^beta (ablation)F^beta · MovieLens tabularPPA level: 0.4869 -> 0Hurt
use F^beta instead of RLHFRLHF · MovieLens tabularPBM policy gain: 0.0611 -> 8.896e-4 (beta=1)Improved
increase beta from 0 to 1 (ablation)F^beta · Synthetic colorwin rate: 0.6157 -> 0.8429Improved
increase beta from 0 to 1 (ablation)F^beta · Synthetic colorPPA level: 0.0883 -> 0.0003Hurt
increase beta from 0 to 1 (ablation)F^beta · Alpaca-GPT4 (expertise)win rate: 0.7613 -> 0.7636No clear effect
increase beta from 0 to 1 (ablation)F^beta · Alpaca-GPT4 (style)PPA level: 0.5012 -> 0.3635Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy