Personalization of Large Language Models: A Survey
Zhehao Zhang, Ryan A. Rossi, Branislav Kveton, Yijia Shao, Diyi Yang, Hamed Zamani, Franck Dernoncourt, Joe Barrow, Tong Yu, Sungchul Kim, Ruiyi Zhang, Jiuxiang Gu, Tyler Derr, Hongjie Chen, Junda Wu, Xiang Chen, Zichao Wang, Subrata Mitra, Nedim Lipka, Nesreen Ahmed, Yu Wang
2024-11-04
Summary
This paper surveys the personalization of Large Language Models (LLMs), exploring how they can be tailored to better meet individual user needs. It discusses the current state of research and proposes a framework to unify different approaches to personalization.
What's the problem?
While personalization of LLMs is becoming more important, most research has focused either on generating personalized text or using LLMs for tasks like recommendation systems. This separation makes it hard to see how these two areas can work together effectively.
What's the solution?
The authors introduce a new framework that categorizes different ways LLMs can be personalized. They define key concepts and challenges in personalization, create systematic taxonomies for various aspects like techniques and datasets, and summarize existing research. This helps bridge the gap between generating personalized content and applying LLMs in personalized applications.
Why it matters?
This research matters because it provides a clearer understanding of how to personalize LLMs, which can improve user experiences in many applications, from chatbots to recommendation systems. By bringing together different approaches, it encourages further innovation in making AI more responsive to individual preferences.
Abstract
Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we bridge the gap between these two separate main directions for the first time by introducing a taxonomy for personalized LLM usage and summarizing the key differences and challenges. We provide a formalization of the foundations of personalized LLMs that consolidates and expands notions of personalization of LLMs, defining and discussing novel facets of personalization, usage, and desiderata of personalized LLMs. We then unify the literature across these diverse fields and usage scenarios by proposing systematic taxonomies for the granularity of personalization, personalization techniques, datasets, evaluation methods, and applications of personalized LLMs. Finally, we highlight challenges and important open problems that remain to be addressed. By unifying and surveying recent research using the proposed taxonomies, we aim to provide a clear guide to the existing literature and different facets of personalization in LLMs, empowering both researchers and practitioners.