# Towards Reward Fairness in RLHF: From a Resource Allocation Perspective

arXiv: https://arxiv.org/abs/2505.23349 · HTML: https://mlsanity.com/paper/2505.23349/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment](https://mlsanity.com/paper/2402.10207/) (2024)
- [WARM: On the Benefits of Weight Averaged Reward Models](https://mlsanity.com/paper/2401.12187/) (2024)
- [HelpSteer2-Preference: Complementing Ratings with Preferences](https://mlsanity.com/paper/2410.01257/) (2024)
- [Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control](https://mlsanity.com/paper/1611.02796/) (2016)
- [Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.05199/) (2023)
- [WARP: On the Benefits of Weight Averaged Rewarded Policies](https://mlsanity.com/paper/2406.16768/) (2024)
- [Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence](https://mlsanity.com/paper/2406.10957/) (2024)
- [Beyond the Binary: Capturing Diverse Preferences With Reward Regularization](https://mlsanity.com/paper/2412.03822/) (2024)
- [Rethinking the Role of Proxy Rewards in Language Model Alignment](https://mlsanity.com/paper/2402.03469/) (2024)
- [Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management](https://mlsanity.com/paper/2104.04748/) (2021)
- [Large Language Models are Biased Reinforcement Learners](https://mlsanity.com/paper/2405.11422/) (2024)

## Built on by (most cited first, 9 of 9)

- [C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs](https://mlsanity.com/paper/2512.23430/) (2025)
- [Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind](https://mlsanity.com/paper/2601.15395/) (2026)
- [Reinforcement Learning from Human Feedback: A Statistical Perspective](https://mlsanity.com/paper/2604.02507/) (2026)
- [Self-Debias: Self-correcting for Debiasing Large Language Models](https://mlsanity.com/paper/2604.08243/) (2026)
- [Linear Social Choice with Few Queries: A Moment-Based Approach](https://mlsanity.com/paper/2603.19510/) (2026)
- [Misaligned by Reward: Socially Undesirable Preferences in LLMs](https://mlsanity.com/paper/2605.05003/) (2026)
- [Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning](https://mlsanity.com/paper/2508.19567/) (2025)
- [ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks](https://mlsanity.com/paper/2605.17458/) (2026)
- [PAFO: Pareto Fairness Optimization for Personalized Reward Modeling](https://mlsanity.com/paper/2606.07988/) (2026)

## Abstract (arXiv)

Rewards serve as proxies for human preferences and play a crucial role in Reinforcement Learning from Human Feedback (RLHF). However, if these rewards are inherently imperfect, exhibiting various biases, they can adversely affect the alignment of large language models (LLMs). In this paper, we collectively define the various biases present in rewards as the problem of reward unfairness. We propose a bias-agnostic method to address the issue of reward fairness from a resource allocation perspective, without specifically designing for each type of bias, yet effectively mitigating them. Specifically, we model preference learning as a resource allocation problem, treating rewards as resources to be allocated while considering the trade-off between utility and fairness in their distribution. We propose two methods, Fairness Regularization and Fairness Coefficient, to achieve fairness in rewards. We apply our methods in both verification and reinforcement learning scenarios to obtain a fairness reward model and a policy model, respectively. Experiments conducted in these scenarios demonstrate that our approach aligns LLMs with human preferences in a more fair manner.