arXiv Machine Learning July 31, 2026 By Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

Read the original on arXiv Machine Learning →

arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.

By Daniel Fein, Max Lamparth, Violet Xiang, Mykel J. Kochenderfer, Nick Haber

llms benchmarks safety

arXiv AI

Sep 1

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment

The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.

By Jialu Wang, Heinrich Peters, Asad A. Butt, Navid Hashemi, Alireza Hashemi, Pouya M. Ghari, Joseph Hoover, James Rae, Morteza Dehghani

llms reinforcement-learning safety

arXiv AI

Jun 8

Re-Centering Humans in LLM Personalization

arXiv:2606. 06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data.

By Lechen Zhang, Jiarui Liu, Tal August

llms

arXiv Computation and Language

Sep 1

Small Language Models as Judges for Rubric-Based Reinforcement Learning

arXiv:2608.30005v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific c...

By Fengyu Xie, Yilun Zhao, Bingsen Chen, Arman Cohan, Chen Zhao

llms reinforcement-learning

arXiv AI

Jun 18

Steerable Cultural Preference Optimization of Reward Models

arXiv:2606. 18606v1 Announce Type: cross Abstract: It is essential for large language model (LLM) technology to serve many different cultural sub-communities in a manner that is acceptable to each community.

By Minsik Oh, Advit Deepak, Sophie Wu, Douwe Kiela, Ekaterina Shutova

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 25

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

arXiv:2505. 12843v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences.

By Kangwen Zhao, Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Dongyun Xue, Wengang Zhou, Li Li, Houqiang Li

llms reinforcement-learning safety

One email a morning, machine-written

Related stories

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment

Re-Centering Humans in LLM Personalization

Small Language Models as Judges for Rubric-Based Reinforcement Learning

Steerable Cultural Preference Optimization of Reward Models

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF