ExplainRec: Towards Explainable Multi-Modal Zero-Shot Recommendation with Preference Attribution and Large Language Models

TL;DR

ExplainRec leverages large language models with multi-modal data and preference attribution to improve explainability, cold-start handling, and recommendation accuracy in multi-modal zero-shot recommendation systems.

Contribution

It introduces a novel framework combining preference attribution, multi-modal fusion, and zero-shot transfer learning for explainable recommendations.

Findings

Outperforms existing methods with 0.7% AUC improvement on MovieLens-25M.

Achieves 0.9% AUC gain on cross-domain recommendation tasks.

Generates interpretable explanations and effectively handles cold-start scenarios.

Abstract

Recent advances in Large Language Models (LLMs) have opened new possibilities for recommendation systems, though current approaches such as TALLRec face challenges in explainability and cold-start scenarios. We present ExplainRec, a framework that extends LLM-based recommendation capabilities through preference attribution, multi-modal fusion, and zero-shot transfer learning. The framework incorporates four technical contributions: preference attribution tuning for explainable recommendations, zero-shot preference transfer for cold-start users and items, multi-modal enhancement leveraging visual and textual content, and multi-task collaborative optimization. Experimental evaluation on MovieLens-25M and Amazon datasets shows that ExplainRec outperforms existing methods, achieving AUC improvements of 0.7\% on movie recommendation and 0.9\% on cross-domain tasks, while generating interpretable explanations and handling cold-start scenarios effectively.