Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters
This work addresses the problem of computational efficiency for deploying language models in domain-specific applications, though it is incremental as it builds on existing adapter-based methods.
The paper tackles the high computational cost of large language models by introducing ALTER, a system that uses Mixture-of-Task-Adapters on small language models (<1B parameters) to handle multiple NLP tasks simultaneously, achieving good performance in experiments.
Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high computational cost of model training and online deployment. In our work, we present ALTER, a system that effectively builds the multi-tAsk Learners with mixTure-of-task-adaptERs upon small language models (with <1B parameters) to address multiple NLP tasks simultaneously, capturing the commonalities and differences between tasks, in order to support domain-specific applications. Specifically, in ALTER, we propose the Mixture-of-Task-Adapters (MTA) module as an extension to the transformer architecture for the underlying model to capture the intra-task and inter-task knowledge. A two-stage training method is further proposed to optimize the collaboration between adapters at a small computational cost. Experimental results over a mixture of NLP tasks show that our proposed MTA architecture and the two-stage training method achieve good performance. Based on ALTER, we have also produced MTA-equipped language models for various domains.