Ensembling Finetuned Language Models for Text Classification
Abstract
Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles of neural networks are typically used to boost performance and provide reliable uncertainty estimates. However, ensembling pretrained models for text classification is not a well-studied avenue. In this paper, we present a metadataset with predictions from five large finetuned models on six datasets, and report results of different ensembling strategies from these predictions. Our results shed light on how ensembling can improve the performance of finetuned text classifiers and incentivize future adoption of ensembles in such tasks.
Cite
@article{arxiv.2410.19889,
title = {Ensembling Finetuned Language Models for Text Classification},
author = {Sebastian Pineda Arango and Maciej Janowski and Lennart Purucker and Arber Zela and Frank Hutter and Josif Grabocka},
journal= {arXiv preprint arXiv:2410.19889},
year = {2024}
}
Comments
Workshop on Fine-Tuning in Modern Machine Learning @ NeurIPS 2024. arXiv admin note: text overlap with arXiv:2410.04520