# ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training

arXiv: https://arxiv.org/abs/2604.07484 · HTML: https://mlsanity.com/paper/2604.07484/

## Key facts

- Cited by 1 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 22 of its 35 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)
- 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, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [Learning to Reason without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [How to Evaluate Reward Models for RLHF](https://mlsanity.com/paper/2410.14872/) (2024)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge](https://mlsanity.com/paper/2501.18099/) (2025)
- [HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages](https://mlsanity.com/paper/2505.11475/) (2025)
- [Can Large Reasoning Models Self-Train?](https://mlsanity.com/paper/2505.21444/) (2025)
- [Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking](https://mlsanity.com/paper/2403.03185/) (2024)
- [Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.08745/) (2025)
- [Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation](https://mlsanity.com/paper/2509.15194/) (2025)
- [Improving Reward Models with Synthetic Critiques](https://mlsanity.com/paper/2405.20850/) (2024)
- [ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism](https://mlsanity.com/paper/2508.11356/) (2025)
- [Learning Code Preference via Synthetic Evolution](https://mlsanity.com/paper/2410.03837/) (2024)
- [Post-Training Large Language Models via Reinforcement Learning from Self-Feedback](https://mlsanity.com/paper/2507.21931/) (2025)
- [Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2512.15146/) (2025)

## Built on by (most cited first, 1 of 1)

- [F2DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows](https://mlsanity.com/paper/2609.19827/) (2026)

## Abstract (arXiv)

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models. However, GRMs face two major challenges: reliance on costly human-annotated data restricts scalability, and self-training approaches often suffer from instability and vulnerability to reward hacking. To address these issues, we propose ConsistRM, a self-training framework that enables effective and stable GRM training without human annotations. ConsistRM incorporates the Consistency-Aware Answer Reward, which produces reliable pseudo-labels with temporal consistency, thereby providing more stable model optimization. Moreover, the Consistency-Aware Critique Reward is introduced to assess semantic consistency across multiple critiques and allocates fine-grained and differentiated rewards. Experiments on five benchmark datasets across four base models demonstrate that ConsistRM outperforms vanilla Reinforcement Fine-Tuning (RFT) by an average of 1.5%. Further analysis shows that ConsistRM enhances output consistency and mitigates position bias caused by input order, highlighting the effectiveness of consistency-aware rewards in improving GRMs. Our implementation is available at https://github.com/yuliangCarmelo/ConsistRM.