LLMs + Persona-Plug = Personalized LLMs
This addresses the need for efficient and effective personalization in language tasks for users, though it is incremental as it builds on existing plug-and-play methods.
The paper tackled the problem of personalizing large language models (LLMs) for diverse user preferences by proposing a lightweight plug-in module that constructs user-specific embeddings from historical contexts, enabling LLMs to generate more personalized outputs without fine-tuning, and it significantly outperformed existing approaches on the LaMP benchmark.
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.