Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning
For practitioners deploying PEFT models in real-world scenarios with limited data and noisy inputs, this work provides a method to enhance robustness, though it is an incremental combination of existing techniques.
The paper proposes SDBN, a framework combining adversarial training with parameter-efficient fine-tuning to improve robustness and generalization in low-resource NLP settings, achieving substantial improvements under word-level and character-level corruptions without adding parameters.
Parameter-Efficient Fine-Tuning (PEFT) has become essential for adapting foundation models to downstream NLP tasks. However, current PEFT methods often struggle with robustness to noise and performance degradation on limited training data. We propose SDBN (Small Data Big Noise), a unified framework that brings adversarial training to PEFT - a combination that remains less studied in the PEFT setting despite its complementary strengths - to enhance model robustness and generalization, outperforming alternative approaches. We also introduce two variants of the method that use discrete uncertainty sets: SDBN-h, which enumerates character-level edits and selects worst-case variants using gradients, and SDBN-p, which uses LLM-generated variants for robust optimization in generative tasks. Experiments across multiple benchmarks reveal substantial improvements, particularly in low-resource settings and under both word-level and character-level corruptions. This framework addresses the less explored intersection of adversarial training and parameter-efficient adaptation, without introducing additional parameters or only modest computational overhead, making PEFT deployments more reliable in real-world scenarios where data scarcity and linguistic variability often coexist