Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models
This addresses the problem of real-time translation for applications like live captioning, though it appears incremental as it adapts existing LLMs to a known bottleneck.
The paper tackles the challenge of applying large language models (LLMs) to simultaneous machine translation (SimulMT), where translation must begin before the full source text is available, by introducing Simul-LLM, the first open-source fine-tuning and evaluation framework for LLMs focused on this task.
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.