# CREAM: Consistency Regularized Self-Rewarding Language Models

arXiv: https://arxiv.org/abs/2410.12735 · HTML: https://mlsanity.com/paper/2410.12735/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 30 of 40)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)

## Built on by (most cited first, 30 of 35)

- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization](https://mlsanity.com/paper/2504.05812/) (2025)
- [Self-Adapting Language Models](https://mlsanity.com/paper/2506.10943/) (2025)
- [Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.08745/) (2025)
- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel](https://mlsanity.com/paper/2412.08467/) (2024)
- [Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models](https://mlsanity.com/paper/2502.08922/) (2025)
- [MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2507.09184/) (2025)
- [Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning](https://mlsanity.com/paper/2509.25534/) (2025)
- [Anyprefer: An Agentic Framework for Preference Data Synthesis](https://mlsanity.com/paper/2504.19276/) (2025)
- [Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens](https://mlsanity.com/paper/2506.08410/) (2025)
- [Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?](https://mlsanity.com/paper/2506.19467/) (2025)
- [SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat](https://mlsanity.com/paper/2506.04721/) (2025)
- [Investigating CoT Monitorability in Large Reasoning Models](https://mlsanity.com/paper/2511.08525/) (2025)
- [Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks](https://mlsanity.com/paper/2509.23067/) (2025)
- [TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning](https://mlsanity.com/paper/2512.13106/) (2025)
- [Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors](https://mlsanity.com/paper/2504.20106/) (2025)
- [Representation Consistency for Accurate and Coherent LLM Answer Aggregation](https://mlsanity.com/paper/2506.21590/) (2025)
- [Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future](https://mlsanity.com/paper/2508.06026/) (2025)
- [DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning](https://mlsanity.com/paper/2510.02341/) (2025)
- [Reward Model Routing in Alignment](https://mlsanity.com/paper/2510.02850/) (2025)
- [Unifying Stable Optimization and Reference Regularization in RLHF](https://mlsanity.com/paper/2602.11523/) (2026)
- [On the Generalization Gap in Self-Evolving Language Model Reasoning](https://mlsanity.com/paper/2606.01075/) (2026)
- [DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations](https://mlsanity.com/paper/2601.00623/) (2026)
- [When Context Returns: Toward Robust Internalization in On-Policy Distillation](https://mlsanity.com/paper/2606.11627/) (2026)
- [Can LLMs Learn to Reason Robustly under Noisy Supervision?](https://mlsanity.com/paper/2604.03993/) (2026)
- [R2V Agent: Teaching SLMs When to Ask for Help](https://mlsanity.com/paper/2605.16604/) (2026)
- [Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories](https://mlsanity.com/paper/2606.03979/) (2026)
- [Value-Free Policy Optimization via Reward Partitioning](https://mlsanity.com/paper/2506.13702/) (2025)

## Abstract (arXiv)

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates responses) and the reward model (which scores and ranks those responses). The ranked responses are then used as preference pairs to train the LLM via direct alignment technologies (e.g. DPO). However, it is noteworthy that throughout this process, there is no guarantee of accuracy in the rewarding and ranking, which is critical for ensuring accurate rewards and high-quality preference data. Empirical results from relatively small LLMs (e.g., 7B parameters) also indicate that improvements from self-rewarding may diminish after several iterations in certain situations, which we hypothesize is due to accumulated bias in the reward system. This bias can lead to unreliable preference data for training the LLM. To address this issue, we first formulate and analyze the generalized iterative preference fine-tuning framework for self-rewarding language model. We then introduce the regularization to this generalized framework to mitigate the overconfident preference labeling in the self-rewarding process. Based on this theoretical insight, we propose a Consistency Regularized sElf-rewarding lAnguage Model (CREAM) that leverages the consistency of rewards across different iterations to regularize the self-rewarding training, helping the model to learn from more reliable preference data. With this explicit regularization, our empirical results demonstrate the superiority of CREAM in improving both reward consistency and alignment performance. The code is publicly available at https://github.com/Raibows/CREAM.