RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models

arXiv:2403.02271v1 Announce Type: cross
Abstract: Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number of model parameters (e.g LoRA). In this study, we explore the impact of altering the input text of the original task in conjunction with parameter-efficient fine-tuning methods. To most effectively rewrite the input text, we train a few-shot paraphrase model with a Maximum-Marginal Likelihood objective. …

abstract arxiv cs.cl cs.lg explore few-shot fine-tuning impact inputs language language models lora parameters processing prompts rephrase researchers riff small study tasks text type