Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
This addresses the problem of deploying high-performance language models in resource-constrained environments, offering an incremental improvement by bridging the gap between small and large models.
The paper tackles the trade-off between computational efficiency and generalization in language models by proposing PiFi, a framework that integrates a frozen layer from a large language model into a small language model and fine-tunes it, achieving consistent performance improvements across NLP tasks without significant computational cost increases.
Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. In contrast, small language models (SLMs) are computationally efficient but often lack the broad generalization capacity of LLMs. To bridge this gap, we propose PiFi, a novel framework that combines the strengths of both LLMs and SLMs to achieve high performance while maintaining efficiency. PiFi integrates a single frozen layer from an LLM into a SLM and fine-tunes the combined model for specific tasks, boosting performance without a significant increase in computational cost. We show that PiFi delivers consistent performance improvements across a range of natural language processing tasks, including both natural language understanding and generation. Moreover, our findings demonstrate PiFi's ability to effectively leverage LLM knowledge, enhancing generalization to unseen domains and facilitating the transfer of linguistic abilities.