paper-with-me

홈 › Papers

DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling

2024-03-02 · Shanghaoran Quan

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various categories of data may cause its generalization performance to suffer from multi-task disturbance, and 2) the human annotation consistency rate is generally only $60\%$ to $75\%$, causing training data to contain a lot of noise. To tackle these two challenges, we introduced the idea of Mixture-of-Experts (MoE) into the field of RM for the first time. We propose the Double-Layer MoE RM (DMoERM). The outer layer MoE is a sparse model. After classifying an input into task categories, we route it to the corresponding inner layer task-specific model. The inner layer MoE is a dense model. We decompose the specific task into multiple capability dimensions and individually fine-tune a LoRA expert on each one. Their outputs are then synthesized by an MLP to compute the final rewards. To minimize costs, we call a public LLM API to obtain the capability preference labels. The validation on manually labeled datasets confirms that our model attains superior consistency with human preference and outstrips advanced generative approaches. Meanwhile, through BoN sampling and RL experiments, we demonstrate that our model outperforms state-of-the-art ensemble methods of RM and mitigates the overoptimization problem. Our code and dataset are available at: https://github.com/quanshr/DMoERM-v1.

📄 PDF Abstract BibTeX arXiv:2403.01197

Code (1)

quanshr/dmoerm 공식 구현 pytorch

Tasks

Language ModellingLarge Language ModelMixture-of-Experts

Similar Papers 제목 키워드 기반

Best Practice Critic Optimization

2026-08-24 · Penghui Qi, Xiangxin Zhou, Wee Sun Lee arxiv

Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prompt. A reliable critic could instead estimate token-level advantages fr…

Reinforcement LearningMathematical Reasoning

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

2026-06-02 · Yifan Wang, Jinyi Mu, Mayank Jobanputra, Yu Wang 외 arxiv

Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values. However, most existing approaches assume a universal reward…

Reinforcement Learning

A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds

2024-05-09 · Christopher Z. Cui, Xiangyu Peng, Mark O. Riedl

Open-ended worlds are those in which there are no pre-specified goals or environmental reward signal. As a consequence, an agent must know how to perform a multitude of tasks. However, when a new task is presented to an …

Few-Shot LearningMixture-of-Experts

PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning

2026-05-01 · Ziqin Yuan, Ruiqi Wang, Dezhong Zhao, Baijian Yang 외 arxiv

Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedback. However, large-scale preference datasets, whether collected from…

Reinforcement Learning

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

2026-02-11 · Yicheng Chen, Zerun Ma, Xinchen Xie, Yining Li 외 arxiv

In the current landscape of Large Language Models (LLMs), the curation of large-scale, high-quality training data is a primary driver of model performance. A key lever is the \emph{data recipe}, which comprises a data pr…

Reinforcement LearningRecipe Generation