ACL Findings2026
Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model
Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on14
- LightGCN: Simplifying and Powering Graph Convolution Network for RecommendationXiangnan He, Kuan Deng, Xiang Wang, Yan Li et al.SIGIR 2020 · 4,448 citations
- Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior RecommendationLianghao Xia, Chao Huang, Yong Xu, Peng Dai et al.AAAI 2021 · 251 citations
- Disentangled Self-Supervision in Sequential RecommendersJianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui et al.KDD 2020 · 223 citations
- An Attentional Recurrent Neural Network for Personalized Next Location RecommendationQing Guo, Zhu Sun, Jie Zhang, Yin-Leng ThengAAAI 2020 · 133 citations
- Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest RecommendationShengyu Zhang, Lingxiao Yang, Dong Yao, Yujie Lu et al.WWW 2022 · 67 citations
Related papers
- HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential RecommendationJingyi Zhou, Cheng Chen, Kai Zuo, Manjie Xu et al.WWW 2026 · 2 citations
- Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMsXiaofei Zhu, Jinfei Chen, Feiyang Yuan, Zhou YangWWW 2026
- Multi-Grained Patch Training for Efficient LLM-based RecommendationJiayi Liao, Ruobing Xie, Sihang Li, Xiang Wang et al.SIGIR 2025 · 3 citations
- LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational RecommendationGuanrong Li, Kuo Tian, Jinnan Qi, Qinghan Fu et al.KDD 2026 · 1 citation
- Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language ModelYu Xia, Rui Zhong, Hao Gu, Wei Yang et al.SIGIR 2025 · 5 citations
