# Detecting Prefix Bias in LLM-based Reward Models

arXiv: https://arxiv.org/abs/2505.13487 · HTML: https://mlsanity.com/paper/2505.13487/

## Key facts

- Cited by 11 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 20 of its 28 references that are in the map.
- First posted on arXiv 13 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, 20 of 20)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Reward Model Ensembles Help Mitigate Overoptimization](https://mlsanity.com/paper/2310.02743/) (2023)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [What's in a Name? Auditing Large Language Models for Race and Gender Bias](https://mlsanity.com/paper/2402.14875/) (2024)
- [Stereotype or Personalization? User Identity Biases Chatbot Recommendations](https://mlsanity.com/paper/2410.05613/) (2024)
- [Rejected Dialects: Biases Against African American Language in Reward Models](https://mlsanity.com/paper/2502.12858/) (2025)

## Built on by (most cited first, 11 of 11)

- [Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization](https://mlsanity.com/paper/2603.08091/) (2026)
- [Biases in the Blind Spot: Detecting What LLMs Fail to Mention](https://mlsanity.com/paper/2602.10117/) (2026)
- [Automatically Finding Reward Model Biases](https://mlsanity.com/paper/2602.15222/) (2026)
- [Reward Models Inherit Value Biases from Pretraining](https://mlsanity.com/paper/2601.20838/) (2026)
- [One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models](https://mlsanity.com/paper/2603.03291/) (2026)
- [Learning Efficient Guardrails for Compliance](https://mlsanity.com/paper/2510.03485/) (2025)
- [compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data](https://mlsanity.com/paper/2602.06669/) (2026)
- [Reward Model Perspectives: Whose Opinions Do Reward Models Reward?](https://mlsanity.com/paper/2510.06391/) (2025)
- [Misaligned by Reward: Socially Undesirable Preferences in LLMs](https://mlsanity.com/paper/2605.05003/) (2026)
- [Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education](https://mlsanity.com/paper/2601.14506/) (2026)
- [Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences](https://mlsanity.com/paper/2604.01312/) (2026)

## Abstract (arXiv)

Reinforcement Learning with Human Feedback (RLHF) has emerged as a key paradigm for task-specific fine-tuning of language models using human preference data. While numerous publicly available preference datasets provide pairwise comparisons of responses, the potential for biases in the resulting reward models remains underexplored. In this work, we introduce novel methods to detect and evaluate prefix bias -- a systematic shift in model preferences triggered by minor variations in query prefixes -- in LLM-based reward models trained on such datasets. We leverage these metrics to reveal significant biases in preference models across racial and gender dimensions. Our comprehensive evaluation spans diverse open-source preference datasets and reward model architectures, demonstrating susceptibility to this kind of bias regardless of the underlying model architecture. Furthermore, we propose a data augmentation strategy to mitigate these biases, showing its effectiveness in reducing the impact of prefix bias. Our findings highlight the critical need for bias-aware dataset design and evaluation in developing fair and reliable reward models, contributing to the broader discourse on fairness in AI.