@inproceedings{mosbach-etal-2023-shot,
title = {Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation},
author = {Marius Mosbach and Tiago Pimentel and Shauli Ravfogel and Dietrich Klakow and Yanai Elazar},
url = {https://aclanthology.org/2023.findings-acl.779},
doi = {https://doi.org/10.18653/v1/2023.findings-acl.779},
year = {2023},
date = {2023},
booktitle = {Findings of the Association for Computational Linguistics: ACL 2023},
pages = {12284-12314},
publisher = {Association for Computational Linguistics},
address = {Toronto, Canada},
abstract = {Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved out-of-domain generalization, and because extensive evidence shows that fine-tuned models pick up on spurious correlations.Unfortunately, previous comparisons of the two approaches were done using models of different sizes. This raises the question of whether the observed weaker out-of-domain generalization of fine-tuned models is an inherent property of fine-tuning or a limitation of the experimental setup. In this paper, we compare the generalization of few-shot fine-tuning and in-context learning to challenge datasets, while controlling for the models used, the number of examples, and the number of parameters, ranging from 125M to 30B. Our results show that fine-tuned language models can in fact generalize well out-of-domain. We find that both approaches generalize similarly; they exhibit large variation and depend on properties such as model size and the number of examples, highlighting that robust task adaptation remains a challenge.},
pubstate = {published},
type = {inproceedings}
}