Zhi-Xiang Li

HyperXRec: Unifying Preference Clusters and LLM Experts for Robust Explainable Recommendations

HyperXRec is a novel framework that unifies preference modeling and explanation generation by integrating hyperspherical latent clustering with a cluster-guided mixture-of-experts (MoE) inside an LLM, resulting in stable and semantically coherent clusters even under sparse interaction settings.