Preference-Optimized Retrieval and Ranking for Efficient Multimodal Recommendation

Large multimodal models (LMMs) exhibit enhanced capabilities in understanding and generating both textual and visual content. By leveraging item metadata, LMMs are also applied for recommendation and demonstrate improvements across diverse scenarios. However, the majority of existing methods explore static item attributes without considering additional contextual information (e.g., price, brand). Moreover, overlooking the interaction between the retrieval and ranking stages may lead to suboptimal solutions for fine-grained recommendations. In this work, we introduce PRIME: preference-optimized retrieval and ranking for efficient multimodal recommendation. PRIME operates in two stages: (i) a lightweight retriever identifies potential candidate items; (ii) an LMM learns to rank the retrieved candidates with detailed user history and multimodal features (e.g., text and image attributes). These features are incorporated into a carefully designed prompt, facilitating fine-grained transition patterns for user preference understanding. To optimize the inference efficiency of PRIME, we introduce verbalizer-based inference, which computes ranking scores for all candidate items in a single forward pass. Furthermore, we employ the LMM ranker to provide feedback on sampled candidate sets, enabling online preference optimization that refines the retriever model and improves the alignment between retrieval and ranking. As a result, PRIME can capture subtle user intentions and efficiently rank candidate items with minimal inference costs. Extensive experiments show the effectiveness and efficiency of PRIME, which consistently achieves superior performance over baseline methods.