CFALR: Collaborative Filtering-Augmented Large Language Model for Personalized Fashion Outfit Recommendation

2026-06-11

AI Summary

This work proposes a novel architecture that integrates collaborative filtering (CF) with large language models (LLMs) to address key challenges in personalized outfit recommendation, including the difficulty of jointly capturing user preferences and aesthetic compatibility, the performance degradation of CF under data sparsity, and the structural rigidity of template-based approaches. By reformulating user–outfit interactions as natural language descriptions, the method leverages LLMs to model fashion semantics and introduces a CF-enhanced generation mechanism to efficiently explore the combinatorial space of clothing items. A trainable projection layer is further incorporated to align the semantic space of language representations with the collaborative interaction space. Evaluated on the Polyvore and IQON benchmarks, the proposed approach significantly outperforms existing CF- and LLM-based methods, achieving state-of-the-art performance in both personalized fill-in-the-blank and outfit generation tasks.

Abstract

Personalized outfit recommendation poses a significant challenge in e-commerce and social media platforms, requiring systems that balance user preferences with aesthetic compatibility. Collaborative filtering (CF) provides a traditional solution for this, but it struggles with data-sparse scenarios and complex user-item-outfit relationships. Meanwhile, existing template-based approaches are constrained by rigid pre-designed structures. To bridge these research gaps, we introduce CFALR (Collaborative Filtering-Augmented Large Language Model for Recommendation), a novel framework that synergizes collaborative filtering with large language models for personalized outfit recommendation. Specifically, CFALR describes user-outfit interactions in natural language and leverages LLMs to capture fashion semantics while employing CF-enhanced embeddings to bridge the semantic space and the collaborative interaction spaces. Our technical contributions include: (1) the first LLM-based architecture specifically designed for personalized outfit recommendation, (2) a CF-augmented generative mechanism that efficiently navigates the extensive combination space of outfit items, and (3) trainable projection layers that optimally integrate relational and content features. Experiments on Polyvore and IQON benchmarks demonstrate CFALR's superior performance over both traditional CF-based and LLM-based methods in personalized fill-in-the-blank and personalized outfit generation tasks.

Problem

• personalized outfit recommendation
• collaborative filtering
• large language models
• fashion semantics
• data sparsity

Innovation

• Collaborative Filtering
• Large Language Model
• Personalized Outfit Recommendation
• Fashion Semantics
• Generative Recommendation