Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
Abstract
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of efficiency, due to the longer input prompt. In this paper, we propose a strategy to make LLMs as efficient as 0-shot text classifiers, while getting comparable or better accuracy than ICL. Our solution targets the low resource setting, i.e., when only 4 examples per class are available. Using a single LLM and few-shot real data we perform a sequence of generation, filtering and Parameter-Efficient Fine-Tuning steps to create a robust and efficient classifier. Experimental results show that our approach leads to competitive results on multiple text classification datasets.
Cite
@article{arxiv.2404.02422,
title = {Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data},
author = {Parth Patwa and Simone Filice and Zhiyu Chen and Giuseppe Castellucci and Oleg Rokhlenko and Shervin Malmasi},
journal= {arXiv preprint arXiv:2404.02422},
year = {2024}
}
Comments
Accepted at LREC-COLING 2024