Collaborative User Prompt for Personalized Generative Recommendation

TL;DR

This paper introduces a novel collaborative soft prompt framework for LLM-based recommender systems that combines individual and shared user preferences using attention mechanisms, improving personalization across multiple recommendation tasks.

Contribution

It proposes an attention-based compositional framework that effectively integrates collaborative signals into personalized prompts for generative recommendation models.

Findings

Improved recommendation accuracy on real-world datasets.

Enhanced personalization by capturing shared user interests.

Versatile performance across different recommendation tasks.

Abstract

Large Language Models (LLMs) have become powerful foundations for generative recommender systems, framing recommendation tasks as text generation tasks. However, existing generative recommendation methods often rely on discrete ID-based prompts or task-specific soft prompts, which overlook the valuable collaborative signals shared among users with similar interests. To address this limitation, this paper presents a compositional framework that integrates a user's individual preferences with collective preferences from similar users to build personalized soft prompts. Specifically, an attention-based mechanism fuses embeddings from users with similar interests, creating a richer representation that captures multiple facets of user preferences. This design dynamically emphasizes shared interests while preserving individual user preferences. Experiments on three real-world datasets demonstrate the effectiveness of the proposed approach across sequential recommendation, top-n recommendation, and explanation generation tasks, underscoring the advantages of incorporating collaborative signals through an attention-based compositional strategy.