Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models

Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Fuad, Lizhong Chen


Abstract
Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processing tasks. Neural machine translation (NMT) is one such task that LLMs have been applied to with great success. However, little research has focused on applying LLMs to the more difficult subset of NMT called simultaneous translation (SimulMT), where translation begins before the entire source context is available to the model. In this paper, we address key challenges facing LLMs fine-tuned for SimulMT, validate classical SimulMT concepts and practices in the context of LLMs, explore adapting LLMs that are fine-tuned for NMT to the task of SimulMT, and introduce Simul-LLM, the first open-source fine-tuning and evaluation pipeline development framework for LLMs focused on SimulMT.
Anthology ID:
2024.acl-long.567
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10530–10541
Language:
URL:
https://aclanthology.org/2024.acl-long.567
DOI:
10.18653/v1/2024.acl-long.567
Bibkey:
Cite (ACL):
Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Fuad, and Lizhong Chen. 2024. Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10530–10541, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models (Agostinelli et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.567.pdf