Parameter Efficient Tuning Allows Scalable Personalization Of Llms For Text Entry: A Case Study On Abbreviation Expansion

Abstract

Abbreviation expansion is a strategy used to speed up communication by limiting the amount of typing and using a language model to suggest expansions. Here we look at personalizing a Large Language Model's (LLM) suggestions based on prior conversations to enhance the relevance of predictions, particularly when the user data is small (~1000 samples). Specifically, we compare fine-tuning, prompt-tun