Deploying Multi-task Online Server with Large Language Model

TL;DR

This paper introduces a three-stage multi-task learning framework for large language models that reduces deployment costs by up to 90.9% while maintaining performance comparable to single-task models.

Contribution

It proposes a novel multi-task learning framework with task filtering and staged fine-tuning, improving efficiency in deploying large language models across multiple tasks.

Findings

Achieves comparable performance to single-task models.

Reduces deployment overhead by up to 90.9%.

Effective across various benchmarks.

Abstract

In the industry, numerous tasks are deployed online. Traditional approaches often tackle each task separately by its own network, which leads to excessive costs for developing and scaling models, especially in the context of large language models. Although multi-task methods can save costs through parameter sharing, they often struggle to outperform single-task methods in real-world applications. To tackle these challenges, we present a three-stage multi-task learning framework for large language models. It involves task filtering, followed by fine-tuning on high-resource tasks, and finally fine-tuning on all tasks. We conducted comprehensive experiments in single-task and multi-task settings. Our approach, exemplified on different benchmarks, demonstrates that it is able to achieve performance comparable to the single-task method while reducing up to 90.9\% of its overhead.