# Improving Reward Models with Synthetic Critiques

arXiv: https://arxiv.org/abs/2405.20850 · HTML: https://mlsanity.com/paper/2405.20850/

## Key facts

- Cited by 44 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 38 of its 55 references that are in the map.
- First posted on arXiv 31 May 2024.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Reward Model Ensembles Help Mitigate Overoptimization](https://mlsanity.com/paper/2310.02743/) (2023)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)

## Built on by (most cited first, 30 of 44)

- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Critique-out-Loud Reward Models](https://mlsanity.com/paper/2408.11791/) (2024)
- [Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge](https://mlsanity.com/paper/2501.18099/) (2025)
- [J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning](https://mlsanity.com/paper/2505.10320/) (2025)
- [HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages](https://mlsanity.com/paper/2505.11475/) (2025)
- [Self-Generated Critiques Boost Reward Modeling for Language Models](https://mlsanity.com/paper/2411.16646/) (2024)
- [TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation](https://mlsanity.com/paper/2410.03608/) (2024)
- [Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks](https://mlsanity.com/paper/2602.05125/) (2026)
- [A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future](https://mlsanity.com/paper/2504.12328/) (2025)
- [Teaching Language Models to Critique via Reinforcement Learning](https://mlsanity.com/paper/2502.03492/) (2025)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models](https://mlsanity.com/paper/2412.02980/) (2024)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [Beyond Scalar Reward Model: Learning Generative Judge from Preference Data](https://mlsanity.com/paper/2410.03742/) (2024)
- [R3: Robust Rubric-Agnostic Reward Models](https://mlsanity.com/paper/2505.13388/) (2025)
- [Uncertainty-Aware Step-wise Verification with Generative Reward Models](https://mlsanity.com/paper/2502.11250/) (2025)
- [Think-J: Learning to Think for Generative LLM-as-a-Judge](https://mlsanity.com/paper/2505.14268/) (2025)
- [HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks](https://mlsanity.com/paper/2503.04378/) (2025)
- [Training Language Models to Critique With Multi-agent Feedback](https://mlsanity.com/paper/2410.15287/) (2024)
- [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://mlsanity.com/paper/2505.16265/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [Reward Modeling from Natural Language Human Feedback](https://mlsanity.com/paper/2601.07349/) (2026)
- [Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models](https://mlsanity.com/paper/2602.04649/) (2026)
- [LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information](https://mlsanity.com/paper/2502.02095/) (2025)
- [mR3: Multilingual Rubric-Agnostic Reward Reasoning Models](https://mlsanity.com/paper/2510.01146/) (2025)
- [Understanding Likelihood Over-optimisation in Direct Alignment Algorithms](https://mlsanity.com/paper/2410.11677/) (2024)
- [Align to Structure: Aligning Large Language Models with Structural Information](https://mlsanity.com/paper/2504.03622/) (2025)
- [PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling](https://mlsanity.com/paper/2510.24235/) (2025)

## Abstract (arXiv)

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost for human annotation. Additionally, RMs tend to quickly overfit on superficial features in the training set, hindering their generalization performance on unseen distributions. We propose a novel approach using synthetic natural language critiques generated by large language models to provide additional feedback, evaluating aspects such as instruction following, correctness, and style. This offers richer signals and more robust features for RMs to assess and score on. We demonstrate that high-quality critiques improve the performance and data efficiency of RMs initialized from different pretrained models, reducing the reliance on costly human annotations. Furthermore, incorporating critiques improves both the interpretability and robustness of RM training.