paper-with-me

홈 › Papers

Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback

2025-05-26 · Mengdi Li, Jiaye Lin, Xufeng Zhao, Wenhao Lu, Peilin Zhao, Stefan Wermter, Di Wang

Reward models trained with conventional Reinforcement Learning from AI Feedback (RLAIF) methods suffer from limited generalizability, which hinders the alignment performance of the policy model during reinforcement learning (RL). This challenge stems from various issues, including distribution shift, preference label noise, and mismatches between overly challenging samples and model capacity. In this paper, we attempt to enhance the generalizability of reward models through a data-centric approach, driven by the insight that these issues are inherently intertwined from the perspective of data difficulty. To address this, we propose a novel framework, $\textit{Curriculum-RLAIF}$, which constructs preference pairs with varying difficulty levels and produces a curriculum that progressively incorporates preference pairs of increasing difficulty for reward model training. Our experimental results suggest that reward models trained with Curriculum-RLAIF achieve improved generalizability, significantly increasing the alignment performance of the policy model by a large margin without incurring additional inference costs compared to various non-curriculum baselines. Detailed analysis and comparisons with alternative approaches, including data selection via external pretrained reward models or internal self-selection mechanisms, as well as other curriculum strategies, further demonstrate the superiority of our approach in terms of simplicity, efficiency, and effectiveness.

📄 PDF Abstract BibTeX arXiv:2505.20075

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Multi-objective Reinforcement learning from AI Feedback

2024-06-11 · Marcus Williams

This paper presents Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF), a novel approach to improving the alignment and performance of language models trained using reinforcement learning from AI feedback …

Language ModelingLanguage ModellingMulti-Objective Reinforcement Learningreinforcement-learning+1

Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback

2025-10-02 · Derek Shi, Ruben Glatt, Christine Klymko, Shubham Mohole 외 arxiv

Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (…

Reinforcement Learning

Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

2024-02-06 · Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang 외

Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs). The previous approaches for VLMMs involved Supervised Fine-Tuning (SFT) with instruction-tuned datase…

Video-based Generative Performance Benchmarking

2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization

2025-04-10 · Mengyang Li, Zhong Zhang

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, tradit…

Model Optimization

HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback

2024-03-13 · Ang Li, Qiugen Xiao, Peng Cao, Jian Tang 외

Reinforcement Learning from AI Feedback (RLAIF) has the advantages of shorter annotation cycles and lower costs over Reinforcement Learning from Human Feedback (RLHF), making it highly efficient during the rapid strategy…

Language ModellingLarge Language ModelRed Teamingreinforcement-learning+2