Cover Image

Information-Theoretic Reward Decomposition for Generalizable RLHF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mao, Liyuan, Xu, Haoran, Zhang, Amy, Zhang, Weinan, Bai, Chenjia
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RLHF Workflow: From Reward Modeling to Online RLHF
by: Dong, Hanze, et al.
Published: (2024)

Reward-Robust RLHF in LLMs
by: Yan, Yuzi, et al.
Published: (2024)

Reward Shaping to Mitigate Reward Hacking in RLHF
by: Fu, Jiayi, et al.
Published: (2025)

CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
by: Wang, Hao, et al.
Published: (2026)

Reward Model Overoptimisation in Iterated RLHF
by: Wolf, Lorenz, et al.
Published: (2025)

How to Evaluate Reward Models for RLHF
by: Frick, Evan, et al.
Published: (2024)

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
by: Mao, Liyuan, et al.
Published: (2024)

Quantile Regression for Distributional Reward Models in RLHF
by: Dorka, Nicolai
Published: (2024)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
by: Chen, Lichang, et al.
Published: (2024)

RewardAnything: Generalizable Principle-Following Reward Models
by: Yu, Zhuohao, et al.
Published: (2025)

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
by: Hu, Jian, et al.
Published: (2024)

Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
by: Zhu, Banghua, et al.
Published: (2024)

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
by: Ono, Shinnosuke, et al.
Published: (2026)

It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
by: Lu, Taiming, et al.
Published: (2024)

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
by: Mao, Liyuan, et al.
Published: (2024)

RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
by: Du, Yuhao, et al.
Published: (2025)

Reward Generalization in RLHF: A Topological Perspective
by: Qiu, Tianyi, et al.
Published: (2024)

An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training
by: Xiao, Youshao, et al.
Published: (2023)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
by: Miao, Yuchun, et al.
Published: (2024)

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
by: Du, Yihan, et al.
Published: (2024)

WPO: Enhancing RLHF with Weighted Preference Optimization
by: Zhou, Wenxuan, et al.
Published: (2024)

RLHF and IIA: Perverse Incentives
by: Xu, Wanqiao, et al.
Published: (2023)

The Perfect Blend: Redefining RLHF with Mixture of Judges
by: Xu, Tengyu, et al.
Published: (2024)

Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
by: Mao, Liyuan, et al.
Published: (2026)

The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models
by: Xu, Xingcheng
Published: (2025)

Adaptive Milestone Reward for GUI Agents
by: Zheng, Congmin, et al.
Published: (2026)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
by: Zhu, Yu, et al.
Published: (2024)

Dataset Reset Policy Optimization for RLHF
by: Chang, Jonathan D., et al.
Published: (2024)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
by: Liang, Kaiqu, et al.
Published: (2025)

General Exploratory Bonus for Optimistic Exploration in RLHF
by: Li, Wendi, et al.
Published: (2025)

Active Preference Optimization for Sample Efficient RLHF
by: Das, Nirjhar, et al.
Published: (2024)

Understanding the Effects of RLHF on LLM Generalisation and Diversity
by: Kirk, Robert, et al.
Published: (2023)

Adaptive Margin RLHF via Preference over Preferences
by: Chittepu, Yaswanth, et al.
Published: (2025)

DPO Meets PPO: Reinforced Token Optimization for RLHF
by: Zhong, Han, et al.
Published: (2024)

Calibrated Surprise: An Information-Theoretic Account of Creative Quality
by: Zou, Bo, et al.
Published: (2026)

PerPO: Perceptual Preference Optimization via Discriminative Rewarding
by: Zhu, Zining, et al.
Published: (2025)

Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback
by: Zheng, Qinqing, et al.
Published: (2024)

Process Rewards with Learned Reliability
by: Li, Jinyuan, et al.
Published: (2026)

Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison
by: Shen, Judy Hanwen, et al.
Published: (2024)