@inproceedings{lin-etal-2024-exploring,
title = {Exploring the Effectiveness and Consistency of Task Selection in Intermediate-Task Transfer Learning},
author = {Pin-Jie Lin and Miaoran Zhang and Marius Mosbach and Dietrich Klakow},
editor = {Xiyan Fu and Eve Fleisig Eve},
url = {https://aclanthology.org/2024.acl-srw.24/},
doi = {https://doi.org/10.18653/v1/2024.acl-srw.24},
year = {2024},
date = {2024},
booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)},
isbn = {979-8-89176-097-4},
pages = {170-185},
publisher = {Association for Computational Linguistics},
address = {Bangkok, Thailand},
abstract = {Identifying beneficial tasks to transfer from is a critical step toward successful intermediate-task transfer learning. In this work, we experiment with 130 source-target task combinations and demonstrate that the transfer performance exhibits severe variance across different source tasks and training seeds, highlighting the crucial role of intermediate-task selection in a broader context. We compare four representative task selection methods in a unified setup, focusing on their effectiveness and consistency. Compared to embedding-free methods and text embeddings, task embeddings constructed from fine-tuned weights can better estimate task transferability by improving task prediction scores from 2.59{\%} to 3.96{\%}. Despite their strong performance, we observe that the task embeddings do not consistently demonstrate superiority for tasks requiring reasoning abilities. Furthermore, we introduce a novel method that measures pairwise token similarity using maximum inner product search, leading to the highest performance in task prediction. Our findings suggest that token-wise similarity is better predictive for predicting transferability compared to averaging weights.},
pubstate = {published},
type = {inproceedings}
}