2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization
2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization
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, traditional DPO methods are limited by their reliance on single preference pairs. Recent work like Curriculum-DPO integrates multiple pairs using a one-dimensional difficulty curriculum based on pairwise distinguishability (PD), but overlooks the complexity of the input prompt itself. To address this, we propose 2D-Curri-DPO, a novel framework employing a two-dimensional curriculum that jointly models Prompt Complexity (PC) and Pairwise Distinguishability. This framework introduces dual difficulty metrics to quantify prompt semantic complexity and response preference clarity, defines a curriculum strategy space encompassing multiple selectable strategies for task adaptation, and incorporates a KL-divergence-based adaptive mechanism for dynamic reference model updates to enhance training stability. Comprehensive experiments demonstrate that 2D-Curri-DPO significantly outperforms standard DPO and prior curriculum methods across multiple benchmarks, including MT-Bench, Vicuna Bench, and WizardLM. Our approach achieves state-of-the-art performance on challenging test sets like UltraFeedback. Ablation studies confirm the benefits of the 2D structure and adaptive mechanisms, while analysis provides guidance for strategy selection. These findings demonstrate that effective alignment requires modeling both prompt complexity and pairwise distinguishability, establishing adaptive, multi-dimensional curriculum learning as a powerful and interpretable new paradigm for preference-based language model optimization.
Mengyang Li、Zhong Zhang
计算技术、计算机技术
Mengyang Li,Zhong Zhang.2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization[EB/OL].(2025-04-10)[2025-04-28].https://arxiv.org/abs/2504.07856.点此复制
评论