Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?

TL;DR

This paper introduces a method to enhance Large Language Models for recommendation tasks by integrating user and item embeddings through lightweight projectors, improving performance over text-only models.

Contribution

The paper presents a novel approach to incorporate collaborative filtering embeddings into LLMs using dedicated projection modules, bridging traditional recommendation data with language models.

Findings

Improved recommendation accuracy over text-only LLM baselines

Effective utilization of structured user-item interaction data

Practical method for combining collaborative filtering with LLMs

Abstract

Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate collaborative signals in a limited manner, typically using only user or item embeddings. These methods struggle to handle multiple item embeddings representing user history, reverting to textual semantics and neglecting richer collaborative information. In this work, we propose a simple yet effective solution that projects user and item embeddings, learned from collaborative filtering, into the LLM token space via separate lightweight projector modules. A finetuned LLM then conditions on these projected embeddings alongside textual tokens to generate recommendations. Preliminary results show that this design effectively leverages structured user-item interaction data, improves recommendation performance over text-only LLM baselines, and offers a practical path for bridging traditional recommendation systems with modern LLMs.