Parameter-efficient fine-tuning of large-scale pre-trained language models

🤖 Plain-English Summary

Abstract With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning paradigm, it has been continuously shown that larger models tend to yield better performance. Additionally, we provide a holistic empirical study on over 100 natural language processing tasks and investigate various aspects of delta-tuning.

🔑 Key Findings

• However, as PLMs scale up, fine-tuning and storing all the parameters is prohibitively costly and eventually becomes practically infeasible.
• This necessitates a new branch of research focusing on the parameter-efficient adaptation of PLMs, which optimizes a small portion of the model parameters while keeping the rest fixed, drastically cutting down computation and storage costs.
• In general, it demonstrates that large-scale models could be effectively stimulated by the optimization of a few parameters.

🔗 Related Resources