Token-Efficient Item Representation via Images for LLM Recommender Systems

Large Language Models (LLMs) have recently emerged as a powerful backbone for recommender systems. Existing LLM-based recommender systems take two different approaches for representing items in natural language, i.e., Attributebased Representation and Description-based Representation. In this work, we aim to address the trade-off between efficiency and effectiveness that these two approaches encounter, when representing items consumed by users. Based on our observation that there is a significant information overlap between images and descriptions associated with items, we propose a novel method, Image representation for LLM-based Recommender system (I-LLMRec). Our main idea is to leverage images as an alternative to lengthy textual descriptions for representing items, aiming at reducing token usage while preserving the rich semantic information of item descriptions. Through extensive experiments on real-world Amazon datasets, we demonstrate that I-LLMRec outperforms existing methods that leverage textual descriptions for representing items in both efficiency and effectiveness by leveraging images. Moreover, a further appeal of I-LLMRec is its ability to reduce sensitivity to noise in descriptions, leading to more robust recommendations. Our code is available at https://github.com/rlqja1107/torch-I-LLMRec . * Corresponding Author 1 While attributes are the high-level, general features in a few keywords (e.g., Apple), descriptions generally provide item-specific details (e.g., It is a slim metallic body, 13-inch Liquid Retina, and black keyboard...).