LLMs + Persona-Plug = Personalized LLMs

TL;DR

This paper introduces \\ours{}, a lightweight personalized LLM approach that creates user-specific embeddings from historical data, enabling better personalization without model fine-tuning, and outperforms existing methods in experiments.

Contribution

The paper proposes a novel user embedding method that enhances personalization in LLMs by modeling user history without fine-tuning the entire model.

Findings

 significantly outperforms existing personalized LLM approaches in experiments.

 effectively captures user preferences through lightweight embeddings.

 improves personalization without requiring model parameter tuning.

Abstract

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, \ours{}. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.