AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models

Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Liu Kang, Fuzhen Li, Zhiyong Zheng, Feng Jiang, Ziheng Li, Kun Yan, Qingyi Si and 3 more

ICML 2026 · Reinforcement learning › RL from feedback · approach: Theory of RLHF · 0 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
add CoT critique before the score (vs score-only output) (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 71.6 -> 74.0Improved
filter out weak-preference samples (scores 0-1) (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 70.7 -> 74.0Improved
add adaptive margin scaled by preference strength (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 72.9 -> 74.0Improved
increase rollout group size from 2 to 4 (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 71.6 -> 74.0Improved
increase rollout group size from 4 to 8 (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 74.0 -> 73.7No clear effect
vary rollout temperature (0.3, 0.7, 1.5 vs 1.0) (ablation)IRPM-Mean Qwen3-8B · RM-Bench + JudgeBenchoverall accuracy: 74.0 -> 72.1 (0.3), 72.5 (0.7), 73.1 (1.5)Hurt
use IRPM-Preference (soft preference strength) as the intergroup reward instead of IRPM-Mean (ablation)IRPM Qwen3-32B · RM-Bench, JudgeBench, RewardBench, PPEaccuracyHurt
use IRPM-Interval (confidence-interval rule reward) instead of IRPM-Mean (ablation)IRPM Qwen3-32B · four reward benchmarksaccuracyHurt
add inference-time voting (average sampled scores)IRPM-Mean-32B · four reward benchmarks (average)average accuracy: 77.2 -> 79.6 (voting@2); 77.2 -> 81.4 (voting@8)Improved
train pointwise GRM with IRPM instead of the backbone aloneLlama-3.1-8B-Instruct · four reward benchmarks (average)average accuracy: 40.1 -> 64.8Improved
use IRPM pointwise GRM vs Bradley-Terry scalar model on same 21k dataQwen3-32B · RM-Bench + JudgeBenchoverall accuracy: 71.6 -> 77.1Improved
use pairwise GRM instead of IRPM pointwise on same dataQwen3-32B · RM-Bench + JudgeBenchoverall accuracy: 77.1 -> 77.7No clear effect

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