Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Song, Huan, Razdan, Deeksha, Qian, Yiyue, Chowdhury, Arijit Ghosh, Patwa, Parth, Chadha, Aman, Zhang, Shinan, Keshava, Sharlina, Marlowe, Hannah
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416055127
Cites:
Cited by:
Related to: