Paper · arXiv 2312.14327
Parameter Efficient Tuning Allows Scalable Personalization of LLMs for Text Entry: A Case Study on Abbreviation Expansion
Katrin Tomanek, Shanqing Cai, Subhashini Venugopalan
Personalizing a large language model's suggestions through fine-tuning, prompt-tuning, and retrieval augmentation enhances relevance, with prompt-tuning and retrieval augmentation outperforming fine-tuning in few-shot scenarios.
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-tuning, and retrieval augmented generation of expanded text suggestions for abbreviated inputs. Our case study with a deployed 8B parameter LLM on a real user living with ALS, and experiments on movie character personalization indicates that (1) customization may be necessary in some scenarios and prompt-tuning generalizes well to those, (2) fine-tuning on in-domain data (with as few as 600 samples) still shows some gains, however (3) retrieval augmented few-shot selection also outperforms fine-tuning. (4) Parameter efficient tuning allows for efficient and scalable personalization. For prompt-tuning, we also find that initializing the learned "soft-prompts" to user relevant concept tokens leads to higher accuracy than random initialization.