# CHARM: Calibrating Reward Models With Chatbot Arena Scores

arXiv: https://arxiv.org/abs/2504.10045 · HTML: https://mlsanity.com/paper/2504.10045/

## Key facts

- Cited by 7 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 25 of its 38 references that are in the map.
- First posted on arXiv 14 Apr 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, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [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)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking](https://mlsanity.com/paper/2312.09244/) (2023)
- [RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style](https://mlsanity.com/paper/2410.16184/) (2024)
- [Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs](https://mlsanity.com/paper/2406.10216/) (2024)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [JudgeLRM: Large Reasoning Models as a Judge](https://mlsanity.com/paper/2504.00050/) (2025)
- [From Lists to Emojis: How Format Bias Affects Model Alignment](https://mlsanity.com/paper/2409.11704/) (2024)
- [Reward Gaming in Conditional Text Generation](https://mlsanity.com/paper/2211.08714/) (2022)
- [Post-hoc Reward Calibration: A Case Study on Length Bias](https://mlsanity.com/paper/2409.17407/) (2024)

## Built on by (most cited first, 7 of 7)

- [R3: Robust Rubric-Agnostic Reward Models](https://mlsanity.com/paper/2505.13388/) (2025)
- [Robust Reward Modeling via Causal Rubrics](https://mlsanity.com/paper/2506.16507/) (2025)
- [TuneJury: An Open Metric for Improving Music Generation Preference Alignment](https://mlsanity.com/paper/2606.17006/) (2026)
- [SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models](https://mlsanity.com/paper/2507.18182/) (2025)
- [Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?](https://mlsanity.com/paper/2510.00766/) (2025)
- [Configurable Reward Model for Balanced Safety Alignment](https://mlsanity.com/paper/2605.30487/) (2026)
- [What do Reward Models Memorize?](https://mlsanity.com/paper/2607.24484/) (2026)

## Abstract (arXiv)

Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. However, they suffer from various biases which could lead to reward hacking. In this paper, we identify a model preference bias in RMs, where they systematically assign disproportionately high scores to responses from certain policy models, leading to unfair judgments. To mitigate this bias, we propose a calibration method named CHatbot Arena calibrated Reward Modeling (CHARM) that leverages Elo scores from the Chatbot Arena to construct debiased preference datasets and adjust reward model scoring. We conduct extensive experiments on reward model benchmarks and human preference alignment. Results demonstrate that our calibrated RMs achieve improved evaluation accuracy on RM-Bench and the Chat-Hard domain of RewardBench, exhibit a stronger correlation with human preferences by producing scores more closely aligned with Elo rankings and improve downstream post-training performance. These results demonstrate that CHARM provides a simple, effective, and broadly applicable approach to building more reliable and fair reward models.