通过分析模型失败模式，自动优化小模型微调的数据增强。
Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models
- 从验证集发现模型错误模式，针对性生成改进数据
- 在Llama 3.2 1B模型上显著提升微调效果
- 适合资源有限但需高精度小模型的场景
小语言模型（SLMs）在部署成本和延迟方面具有显著优势，但在复杂领域任务上的准确性常落后于大模型。尽管监督微调可缩小性能差距，但需大量手动数据准备与迭代优化。本文提出PaDA-Agent（模式引导的数据增强代理），一种评估驱动的方法，通过协同操作简化小模型的数据增强流程。不同于仅关注训练误差并生成纠错样本的现有方法，PaDA-Agent通过评估从验证数据中发现失败模式，并制定针对性的数据增强策略，直接缩小泛化差距。实验表明，该方法在Llama 3.2 1B Instruct模型微调中显著优于当前主流基于大模型的数据增强方法。
原文摘要 · Abstract (English)
Small Language Models (SLMs) offer compelling advantages in deployment cost and latency, but their accuracy often lags behind larger models, particularly for complex domain-specific tasks. While supervised fine-tuning can help bridge this performance gap, it requires substantial manual effort in data preparation and iterative optimization. We present PaDA-Agent (Pattern-guided Data Augmentation Agent), an evaluation-driven approach that streamlines the data augmentation process for SLMs through coordinated operations. Unlike state-of-the-art approaches that focus on model training errors only and generating error-correcting samples, PaDA-Agent discovers failure patterns from the validation data via evaluations and drafts targeted data augmentation strategies aiming to directly reduce the generalization gap. Our experimental results demonstrate significant improvements over state-of-the-art LLM-based data augmentation approaches for Llama 3.2 1B Instruct model fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。