reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs
Abstract
Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase performance on standard benchmarks, this may partly be due to overfitting effects, which would confound an understanding of their true capability. In this work, we scrutinize the robustness of reward models and the extent of such overfitting. We build **reWordBench**, which systematically transforms reward model inputs in meaning- or ranking-preserving ways. We show that state-of-the-art reward models suffer from substantial performance degradation even with minor input transformations, sometimes dropping to significantly below-random accuracy, suggesting brittleness. To improve reward model robustness, we propose to explicitly train them to assign similar scores to paraphrases, and find that this approach also improves robustness to other distinct kinds of transformations. For example, our robust reward model reduces such degradation by roughly half for the Chat Hard subset in RewardBench. Furthermore, when used in alignment, our robust reward models demonstrate better utility and lead to higher-quality outputs, winning in up to 59% of instances against a standardly trained RM.
Community
We show that SOTA reward models are brittle and flip predictions when inputs are slightly transformed. We also demonstrate a simple method to improve reward model robustness.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- IPO: Your Language Model is Secretly a Preference Classifier (2025)
- Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference (2025)
- Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025)
- From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning (2025)
- SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models (2025)
- RAG-Reward: Optimizing RAG with Reward Modeling and RLHF (2025)
- InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper