ACL Findings2026
HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
Guorui Li, Dugang Liu, Lei Li, Xing Tang, Zhong Ming
Abstract
Large language model (LLM)-enhanced sequential recommendation typically aims to improve two core components: user semantic embedding extraction and utilization. Despite promising results, existing methods still have two limitations: 1) In the extraction stage, most methods directly input long interaction sequence fragments into LLM for preference summarization. However, excessively long sequences increase inference difficulty, making it challenging to reliably infer accurate user embeddings. 2) In the utilization stage, most methods employ the same semantic embedding utilization strategy for all users, neglecting the differences caused by user activity levels, leading to suboptimal performance. To address these issues, we propose HSUGA, which introduces a simple yet effective plugin for each of the two core components: Hierarchical Semantic Understanding (HSU) and Group-Aware Alignment (GAA). HSU performs a staged twophase preference mining and models preference evolution through constrained editing operations, thereby improving the reliability of user semantic extraction. GAA adjusts the intensity of semantic utilization based on user activity levels, providing weaker alignment for active users and stronger guidance for users with sparse historical data. Finally, extensive experiments on three benchmark datasets demonstrate the effectiveness and compatibility of HSUGA.
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 on8
- MemoryBank: Enhancing Large Language Models with Long-Term MemoryWanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye et al.AAAI 2024 · 394 citations
- Representation Learning with Large Language Models for RecommendationXubin Ren, Wei Wei, Lianghao Xia, Lixin Su et al.WWW 2024 · 385 citations
- Augmenting Language Models with Long-Term MemoryWeizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu et al.NeurIPS 2023 · 256 citations
- Harnessing Large Language Models for Text-Rich Sequential RecommendationZhi Zheng, Wenshuo Chao, Zhaopeng Qiu, Hengshu Zhu et al.WWW 2024 · 114 citations
- MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential RecommendationKibum Kim, Dongmin Hyun, Sukwon Yun, Chanyoung ParkSIGIR 2023 · 31 citations
Related papers
- SEAR: LLM-Powered Sequential Recommendation via Fusion of Collaborative, Semantic, and Rating InformationWei Guan, Jian Cao, Qiqi Cai, Jianqi Gao et al.WWW 2026
- SAGE: Global Semantic Alignment with LLMs for Long-Tail Sequential RecommendationMaolin Wang, Tongshu Bian, Ziyan Wang, Xiaotong Jiang et al.WWW 2026
- 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
- Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential RecommendationZhifu Wei, Yizhou Dang, Guibing Guo, Chuang Zhao et al.SIGIR 2026
- LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential RecommendationYingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma et al.KDD 2025 · 2 citations
