IT-Tuning : Parameter Efficient Information Token Tuning for Language Model

Jungu Kim, Hyeoncheol Kim


Abstract
Recently, language models have demonstrated exceptional performance compared to their predecessors. In this context, attention mechanisms and pre-training significantly contribute to the enhanced performance of modern language models. Additionally, a continuously increasing number of parameters plays a crucial role in these advancements . However, an increase in the number of parameters significantly increases the GPU memory and training time required during fine-tuning of language models, this makes fine-tuning infeasible in environments with limited computing resources. Furthermore, after fine-tuning, the storage space required for deployment increases proportionally with the number of tasks, making it challenging to deploy devices with limited storage capacities. In this study, we propose IT-Tuning, a Parameter Efficient Fine-Tuning method that introduces a new concept called information tokens to address these issues.
Anthology ID:
2024.repl4nlp-1.6
Volume:
Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Chen Zhao, Marius Mosbach, Pepa Atanasova, Seraphina Goldfarb-Tarrent, Peter Hase, Arian Hosseini, Maha Elbayad, Sandro Pezzelle, Maximilian Mozes
Venues:
RepL4NLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–68
Language:
URL:
https://aclanthology.org/2024.repl4nlp-1.6
DOI:
Bibkey:
Cite (ACL):
Jungu Kim and Hyeoncheol Kim. 2024. IT-Tuning : Parameter Efficient Information Token Tuning for Language Model. In Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024), pages 58–68, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
IT-Tuning : Parameter Efficient Information Token Tuning for Language Model (Kim & Kim, RepL4NLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.repl4nlp-1.6.pdf