Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model

Large language models (LLMs) show potential for multi-interest analysis of users in recommender systems, going beyond heuristic assumptions in existing methods, e.g., cooccurring items indicate the same interest. Despite the effectiveness, two key challenges remain. First, the granularity of raw generation of LLMs for multi-interests is agnostic, possibly leading to overly fine or coarse interest grouping. Second, adopting LLM to analyze individual user behaviors lacks a global perspective on how items relate across users. In this paper, we propose an LLM-driven adaptive and representative multi-interest modeling framework to address the challenges. At the user-individual level, we exploit LLM analysis and alleviate the agnostic granularity by adaptively aggregating semantic clusters to collaborative multiinterests. At the user-crowd level, to mitigate the limited insights in individual behaviors, we formulate a max covering problem to expand the scope of LLM analysis with compactness and representativeness, disentangling interest representations from global perspectives. Experiments on real-world datasets show that our approach outperforms various baselines.