Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings
This work addresses the labeling bottleneck for researchers and practitioners in low-resource domains and languages, but it is incremental as it explores an unexplored interplay between existing techniques.
The study tackled the problem of fine-tuning pre-trained language models in low-resource settings by combining active learning with parameter-efficient fine-tuning, finding that PEFT outperforms full fine-tuning and maintains this advantage in active learning setups with more stable representations.
Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages. Active learning (AL), a set of algorithms designed to decrease labeling costs by minimizing label complexity, has shown promise in confronting the labeling bottleneck. In parallel, adapter modules designed for parameter-efficient fine-tuning (PEFT) have demonstrated notable potential in low-resource settings. However, the interplay between AL and adapter-based PEFT remains unexplored. We present an empirical study of PEFT behavior with AL in low-resource settings for text classification tasks. Our findings affirm the superiority of PEFT over full-fine tuning (FFT) in low-resource settings and demonstrate that this advantage persists in AL setups. We further examine the properties of PEFT and FFT through the lens of forgetting dynamics and instance-level representations, where we find that PEFT yields more stable representations of early and middle layers compared to FFT. Our research underscores the synergistic potential of AL and PEFT in low-resource settings, paving the way for advancements in efficient and effective fine-tuning.