Research Papers 论文研究 3d ago Updated 2d ago 更新于 2天前 48

Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training Data-DPO:直接偏好优化用于LLM后训练的目标模型数据选择

Data-DPO introduces a target model-oriented approach to SFT data selection, addressing the gap in existing methods that treat data value as static rather than model-compatible The method uses one-step probing to observe local training feedback, converting activation differences into pairwise data preferences for a lightweight reward model Data-DPO combines target model preferences, external quality scores, and marginal diversity to construct stable and effective training subsets Experiments on V 提出Data-DPO方法,用于LLM后训练阶段的目标模型导向SFT数据选择 通过单步探测观察目标模型在不同样本上的局部训练反馈,将激活差异转化为成对数据偏好 训练轻量级奖励模型学习目标模型感知的数据偏好 最终选择阶段结合目标模型偏好、外部质量评分和边际多样性构建训练子集 在Vision-Flan和LLaVA-CoT基准上,Data-DPO在多种数据预算下均优于现有基线,并稳定超越全量数据训练性能

65
Hot 热度
72
Quality 质量
68
Impact 影响力

Analysis 深度分析

TL;DR

  • Data-DPO introduces a target model-oriented approach to SFT data selection, addressing the gap in existing methods that treat data value as static rather than model-compatible
  • The method uses one-step probing to observe local training feedback, converting activation differences into pairwise data preferences for a lightweight reward model
  • Data-DPO combines target model preferences, external quality scores, and marginal diversity to construct stable and effective training subsets
  • Experiments on Vision-Flan and LLaVA-CoT demonstrate consistent outperformance over existing baselines across multiple data budgets
  • Data-DPO stably surpasses full data training performance, suggesting that intelligent data selection can exceed the utility of training on all available data

Why It Matters

This work addresses a critical bottleneck in LLM post-training: the inefficiency of using all available data for supervised fine-tuning. By making data selection adaptive to the target model's capability distribution, Data-DPO offers a practical pathway to reduce training costs while improving or maintaining performance. For AI practitioners managing large-scale fine-tuning pipelines, this approach could significantly lower compute requirements without sacrificing model quality.

Technical Details

  • One-step probing mechanism: Data-DPO performs a single training step on candidate samples to observe the target model's local training feedback, capturing how different data points affect the model's activations
  • Pairwise preference construction: Activation differences across samples are transformed into pairwise data preferences, enabling a preference-based ranking rather than absolute scoring
  • Lightweight reward model: A compact reward model is trained to learn target-model-aware data preferences, making the selection process computationally efficient
  • Multi-factor selection strategy: The final training subset is constructed by combining three signals: target model preference, external quality scores, and marginal diversity, balancing performance, quality, and coverage
  • Benchmarks: Evaluated on Vision-Flan and LLaVA-CoT datasets, demonstrating robustness across multiple data budgets and consistent superiority over full-data training

Industry Insight

  • The shift from static to dynamic data valuation represents a paradigm change in data curation; practitioners should consider model-aware selection strategies rather than relying solely on heuristic or quality-based filtering
  • The combination of preference learning with diversity optimization offers a template for future data selection systems, particularly in resource-constrained environments where full-data training is infeasible
  • As LLM post-training increasingly dominates compute budgets, methods like Data-DPO that can match or exceed full-data performance with subsets will become essential for scaling efficient training pipelines

TL;DR

  • 提出Data-DPO方法,用于LLM后训练阶段的目标模型导向SFT数据选择
  • 通过单步探测观察目标模型在不同样本上的局部训练反馈,将激活差异转化为成对数据偏好
  • 训练轻量级奖励模型学习目标模型感知的数据偏好
  • 最终选择阶段结合目标模型偏好、外部质量评分和边际多样性构建训练子集
  • 在Vision-Flan和LLaVA-CoT基准上,Data-DPO在多种数据预算下均优于现有基线,并稳定超越全量数据训练性能

为什么值得看

本文针对SFT数据选择中数据价值被视为静态属性的问题,提出了目标模型导向的数据选择新范式,对降低训练成本同时保持模型性能具有重要实践价值。

技术解析

  • 核心问题:现有数据选择方法将数据价值视为静态属性,忽视了数据与目标模型能力分布的兼容性
  • 单步探测机制:通过一步探针观察目标模型在不同样本上的局部训练反馈,将激活差异转化为成对数据偏好
  • 轻量级奖励模型:训练一个轻量级奖励模型来学习目标模型感知的数据偏好
  • 三元选择策略:最终选择阶段结合目标模型偏好、外部质量评分和边际多样性三个维度构建训练子集
  • 实验验证:在Vision-Flan和LLaVA-CoT数据集上验证,Data-DPO在多种数据预算下均优于现有基线,且稳定超越全量数据训练性能

行业启示

  • 数据选择范式转变:从静态数据价值评估转向动态目标模型感知,为SFT数据筛选提供了更精准的方法论
  • 训练效率优化:通过智能数据选择可在减少训练数据量的同时保持甚至提升模型性能,显著降低计算成本
  • 工程实践价值:轻量级奖励模型的设计思路易于落地,适合资源受限场景下的模型微调优化

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

LLM 大模型 Fine-tuning 微调 Training 训练 Research 科学研究 Alignment 对齐