COLING 2024main2 citations

Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data

Parth Patwa, Simone Filice, Zhiyu Chen, Giuseppe Castellucci, Oleg Rokhlenko, Shervin Malmasi

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.

BibTeX
@inproceedings{patwa-etal-2024-enhancing,
    title = "Enhancing Low-Resource {LLM}s Classification with {PEFT} and Synthetic Data",
    author = "Patwa, Parth  and
      Filice, Simone  and
      Chen, Zhiyu  and
      Castellucci, Giuseppe  and
      Rokhlenko, Oleg  and
      Malmasi, Shervin",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.533/",
    pages = "6017--6023"
}
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data · COLING 2024