Tiny Reward Models

• URL: http://arxiv.org/abs/2507.09973v1
• Date: Mon, 14 Jul 2025 06:43:00 GMT
• Title: Tiny Reward Models
• Authors: Sarah Pan,
• Abstract summary: We present TinyRM, a family of small, bidirectional masked language models (MLMs) with as few as 400 million parameters.<n>TinyRM combines FLAN-style prompting, Directional Low-Rank Adaptation (DoRA), and layer freezing to achieve strong performance on RewardBench.<n>Our experiments suggest that small models benefit from domain-specific tuning strategies, particularly in reasoning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large decoder-based language models have become the dominant architecture for reward modeling in reinforcement learning from human feedback (RLHF). However, as reward models are increasingly deployed in test-time strategies, their inference costs become a growing concern. We present TinyRM, a family of small, bidirectional masked language models (MLMs) with as few as 400 million parameters, that rival the capabilities of models over 175 times larger on reasoning and safety preference modeling tasks. TinyRM combines FLAN-style prompting, Directional Low-Rank Adaptation (DoRA), and layer freezing to achieve strong performance on RewardBench, despite using significantly fewer resources. Our experiments suggest that small models benefit from domain-specific tuning strategies, particularly in reasoning, where lightweight finetuning methods are especially effective. While challenges remain in building generalist models and conversational preference modeling, our preliminary results highlight the promise of lightweight bidirectional architectures as efficient, scalable alternatives for preference modeling.

Related papers

• Activation Reward Models for Few-Shot Model Alignment [77.37511364793515]
  We introduce Activation Reward Models (Activation RMs)<n>Activation RMs leverage activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning.<n>We demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications.
  arXiv  Detail & Related papers  (2025-07-02T05:10:29Z)
• Bi-directional Model Cascading with Proxy Confidence [3.1890398692194326]
  We propose a bi-directional approach to deferral that considers the confidence of small and large models in the cascade simultaneously.<n>We use an analysis of hidden states to improve post-invocation confidence of the small model.<n>We then combine this with a tiny proxy model to estimate pre-invocation confidence of the large model.
  arXiv  Detail & Related papers  (2025-04-27T23:48:14Z)
• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs)<n>We introduce a $textbfR$esponse-$textbfc$onditioned $textbfB$radley-$textbfT$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following.<n>We also propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style [37.97757796124621]
  RM-Bench is a novel benchmark designed to evaluate reward models based on their sensitivity to subtle content differences and resistance to style biases. We evaluate nearly 40 reward models on RM-Bench and find that even state-of-the-art models achieve an average performance of only 46.6%.
  arXiv  Detail & Related papers  (2024-10-21T16:48:26Z)
• Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities [4.389938747401259]
  This work explores the effects of fine-tuning strategies on Large Language Models (LLMs) in domains such as materials science and engineering. We find that the merging of multiple fine-tuned models can lead to the emergence of capabilities that surpass the individual contributions of the parent models.
  arXiv  Detail & Related papers  (2024-09-05T11:49:53Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training [32.154166415680066]
  Methods like distillation, compression or quantization help leverage the highly performant large models to induce smaller performant ones. This paper explores the hypothesis that a single training run can simultaneously train a larger model for performance and derive a smaller model for deployment.
  arXiv  Detail & Related papers  (2024-02-07T17:07:41Z)
• Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression [64.07696663255155]
  Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these models poses huge challenges for their deployment in real-world applications. We introduce a novel compression paradigm called Retrieval-based Knowledge Transfer (RetriKT) which effectively transfers the knowledge of LLMs to extremely small-scale models.
  arXiv  Detail & Related papers  (2023-10-24T07:58:20Z)
• Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning [56.50123642237106]
  Common practice in model-based reinforcement learning is to learn models that model every aspect of the agent's environment. We argue that such models are not particularly well-suited for performing scalable and robust planning in lifelong reinforcement learning scenarios. We propose new kinds of models that only model the relevant aspects of the environment, which we call "minimal value-minimal partial models"
  arXiv  Detail & Related papers  (2023-01-24T16:40:01Z)
• METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals [151.3601429216877]
  We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. We propose a recipe, namely "Model generated dEnoising TRaining Objective" (METRO) The resultant models, METRO-LM, consisting of up to 5.4 billion parameters, achieve new state-of-the-art on the GLUE, SuperGLUE, and SQuAD benchmarks.
  arXiv  Detail & Related papers  (2022-04-13T21:39:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.