# CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling

arXiv: https://arxiv.org/abs/2410.21545 · HTML: https://mlsanity.com/paper/2410.21545/

## Key facts

- Cited by 22 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 21 of its 33 references that are in the map.
- First posted on arXiv 28 Oct 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, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking](https://mlsanity.com/paper/2312.09244/) (2023)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Noise Contrastive Alignment of Language Models with Explicit Rewards](https://mlsanity.com/paper/2402.05369/) (2024)
- [RRM: Robust Reward Model Training Mitigates Reward Hacking](https://mlsanity.com/paper/2409.13156/) (2024)

## Built on by (most cited first, 22 of 22)

- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling](https://mlsanity.com/paper/2510.17314/) (2025)
- [Robust Reward Modeling via Causal Rubrics](https://mlsanity.com/paper/2506.16507/) (2025)
- [Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation](https://mlsanity.com/paper/2602.03619/) (2026)
- [MORQA: Benchmarking Evaluation Metrics for Medical Open-Ended Question Answering](https://mlsanity.com/paper/2509.12405/) (2025)
- [Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge](https://mlsanity.com/paper/2605.30568/) (2026)
- [Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis](https://mlsanity.com/paper/2602.00846/) (2026)
- [Visual Preference Optimization with Rubric Rewards](https://mlsanity.com/paper/2604.13029/) (2026)
- [GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation](https://mlsanity.com/paper/2608.29856/) (2026)
- [Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards](https://mlsanity.com/paper/2605.26579/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents](https://mlsanity.com/paper/2606.21262/) (2026)
- [C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences](https://mlsanity.com/paper/2604.13618/) (2026)
- [Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning](https://mlsanity.com/paper/2608.02831/) (2026)
- [Test-Time Scaling via Error Localization](https://mlsanity.com/paper/2607.21453/) (2026)
- [Task-Adaptive Rubrics for GUI Reward Modeling](https://mlsanity.com/paper/2608.24174/) (2026)
- [Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning](https://mlsanity.com/paper/2601.04695/) (2026)
- [RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments](https://mlsanity.com/paper/2604.18026/) (2026)
- [Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?](https://mlsanity.com/paper/2605.29857/) (2026)
- [RLVR2: Reinforcement Learning with Verifiable Rubric-based Ranking](https://mlsanity.com/paper/2609.23457/) (2026)
- [PRISM: Calibrating Black-Box Judges with Counterfactual Probes](https://mlsanity.com/paper/2610.18389/) (2026)

## Abstract (arXiv)

Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In reinforcement learning from human feedback (RLHF) and more generally during post-training flawed reward signals often lead to outputs that optimize for these spurious correlates instead of genuine quality or correctness. We propose Context-Aware Reward Modeling (CARMO), a novel approach that first generates dynamic, context-relevant criteria to ground the reward model before producing reward scores. Unlike prior methods that rely on static rubrics, CARMO leverages large language models (LLMs) to adaptively create evaluation criteria such as logical consistency, clarity, and depth tailored to the user query. Our theoretical analysis shows that such criteria generation can mitigate reward hacking. We further demonstrate that CARMO can be distilled into smaller models, reducing the computational cost of alignment. We establish a new state-of-the-art performance in zero-shot settings for generative models, achieving a 2.1% improvement on Reward Bench. Furthermore, alignment performed on the CARMO-curated preference dataset achieves 22.5% and 21.1% LC-WR and WR, respectively, on Mistral-Base (7B).