Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization

Alexandra Chronopoulou, Jonas Pfeiffer, Joshua Maynez, Xinyi Wang, Sebastian Ruder, Priyanka Agrawal


Abstract
Parameter-efficient fine-tuning (PEFT) using labeled task data can significantly improve the performance of large language models (LLMs) on the downstream task. However, there are 7000 languages in the world and many of these languages lack labeled data for real-world language generation tasks. In this paper, we propose to improve zero-shot cross-lingual transfer by composing expert modules trained separately on language or task data. Our method composes language and task PEFT adapters via element-wise arithmetic operations to leverage unlabeled data and English labeled data. We extend our approach to cases where labeled data from more languages is available and propose to arithmetically compose PEFT adapters trained on languages related to the target. Empirical results on summarization demonstrate that our method is a strategy that obtains consistent gains using minimal training of PEFT parameters.
Anthology ID:
2024.mrl-1.7
Volume:
Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Jonne Sälevä, Abraham Owodunni
Venue:
MRL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
114–126
Language:
URL:
https://aclanthology.org/2024.mrl-1.7
DOI:
Bibkey:
Cite (ACL):
Alexandra Chronopoulou, Jonas Pfeiffer, Joshua Maynez, Xinyi Wang, Sebastian Ruder, and Priyanka Agrawal. 2024. Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 114–126, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization (Chronopoulou et al., MRL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.mrl-1.7.pdf