Search papers, labs, and topics across Lattice.
This paper introduces ProMax, a recommendation framework that leverages LLM-derived user and item profiles to enhance collaborative filtering. ProMax uses dense retrieval to identify relationships between user and item profiles and then employs a dual distribution-reshaping process to guide the recommendation model. Experiments on three public datasets demonstrate that ProMax significantly improves the performance of several base recommendation models and outperforms existing LLM-based recommendation approaches.
LLM-derived user profiles can be powerfully leveraged for recommendation via a surprisingly simple distribution shaping approach, outperforming more complex fusion methods.
The remarkable text understanding and generation capabilities of large language models (LLMs) have revitalized the field of general recommendation based on implicit user feedback. Rather than deploying LLMs directly as recommendation models, a more flexible paradigm leverages their ability to interpret users' historical interactions and semantic contexts to extract structured profiles that characterize user preferences. These profiles can be further transformed into actionable high-dimensional representations, serving as powerful signals to augment and strengthen recommendation models. However, the mechanism by which such profiles enhance recommendation performance within the feature space remains insufficiently understood. Moreover, existing studies predominantly rely on nonlinear alignment and fusion strategies to incorporate these profiles, which often lead to semantic loss and fail to fully exploit their potential. To address these limitations, we revisit profiles from a retrieval perspective and propose a simple yet effective recommendation framework built upon distribution shaping (ProMax) in this paper. We begin by employing dense retrieval to uncover the collaborative relationships between user and item profiles within the feature space. Based on this insight, we introduce a dual distribution-reshaping process, in which the profile distribution acts as a guiding signal to steer the recommendation model toward learning user preferences for unseen items beyond the scope of observed interactions. We apply ProMax to four classic recommendation methods on three public datasets. The results indicate that ProMax substantially improves base model performance and outperforms existing LLM-based recommendation approaches.
