PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization

TL;DR

This paper introduces PEFT-U, a benchmark dataset for personalizing large language models to better accommodate individual user preferences, addressing the limitations of universal models in capturing human diversity.

Contribution

The paper presents PEFT-U, a new dataset for evaluating personalized NLP models and explores efficient fine-tuning methods for user-specific adaptation of LLMs.

Findings

PEFT-U enables assessment of personalization in NLP models.

Efficient fine-tuning improves user-specific task performance.

Benchmark highlights diversity in user preferences.

Abstract

The recent emergence of Large Language Models (LLMs) has heralded a new era of human-AI interaction. These sophisticated models, exemplified by Chat-GPT and its successors, have exhibited remarkable capabilities in language understanding. However, as these LLMs have undergone exponential growth, a crucial dimension that remains understudied is the personalization of these models. Large foundation models such as GPT-3 etc. focus on creating a universal model that serves a broad range of tasks and users. This approach emphasizes the model's generalization capabilities, treating users as a collective rather than as distinct individuals. While practical for many common applications, this one-size-fits-all approach often fails to address the rich tapestry of human diversity and individual needs. To explore this issue we introduce the PEFT-U Benchmark: a new dataset for building and evaluating NLP models for user personalization. \datasetname{} consists of a series of user-centered tasks containing diverse and individualized expressions where the preferences of users can potentially differ for the same input. Using PEFT-U, we explore the challenge of efficiently personalizing LLMs to accommodate user-specific preferences in the context of diverse user-centered tasks.