LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
Keywords: simultaneous machine translation, machine translation, Large Language Models, adaptive policy, supervised fine-tuning
TL;DR: This paper proposes a novel paradigm for enabling large language models (LLMs) to efficiently and adptively perform high-quality simultaneous machine translation.
Abstract: When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt *"Translate the following sentence from [src lang] into [tgt lang]:"*.
However, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation (SiMT) is required, then the **efficiency** and **performance** of decoder-only LLMs are significantly limited by their auto-regressive nature.
To enable LLMs to achieve high-quality SiMT as efficiently as offline translation, we propose a novel paradigm that includes constructing supervised fine-tuning (SFT) data for SiMT, along with new training and inference strategies.
To replicate the token input/output (I/O) stream in SiMT, the source and target tokens are rearranged into an interleaved sequence, separated by special tokens according to varying latency requirements.
This enables powerful LLMs to learn read and write operations adaptively, based on varying latency prompts, while still maintaining efficient auto-regressive decoding.
Experimental results demonstrate that, even with limited SFT data, our approach achieves state-of-the-art performance across various simultaneous translation benchmarks and different evaluation metrics, and preserves the original capabilities of offline translation.
Moreover, EAST generalizes well to document-level SiMT without requiring specific fine-tuning, even beyond the offline translation model.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6257
Loading