LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation

• URL: http://arxiv.org/abs/2507.10917v2
• Date: Thu, 17 Jul 2025 15:01:08 GMT
• Title: LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation
• Authors: Ziyan Wang, Yingpeng Du, Zhu Sun, Jieyi Bi, Haoyan Chua, Tianjun Wei, Jie Zhang,
• Abstract summary: Large language models (LLMs) show significant potential for multi-interest analysis due to their extensive knowledge and powerful reasoning capabilities.<n>We propose an LLM-driven dual-level multi-interest modeling framework for more effective recommendation.<n> Experiments on real-world datasets show the superiority of our approach against state-of-the-art methods.
• Score: 12.89199121698673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, much effort has been devoted to modeling users' multi-interests based on their behaviors or auxiliary signals. However, existing methods often rely on heuristic assumptions, e.g., co-occurring items indicate the same interest of users, failing to capture user multi-interests aligning with real-world scenarios. While large language models (LLMs) show significant potential for multi-interest analysis due to their extensive knowledge and powerful reasoning capabilities, two key challenges remain. First, the granularity of LLM-driven multi-interests is agnostic, possibly leading to overly fine or coarse interest grouping. Second, individual user analysis provides limited insights due to the data sparsity issue. In this paper, we propose an LLM-driven dual-level multi-interest modeling framework for more effective recommendation. At the user-individual level, we exploit LLMs to flexibly allocate items engaged by users into different semantic clusters, indicating their diverse and distinct interests. To alleviate the agnostic generation of LLMs, we adaptively assign these semantic clusters to users' collaborative multi-interests learned from global user-item interactions, allowing the granularity to be automatically adjusted according to the user's behaviors using an alignment module. To alleviate the limited insights derived from individual users' behaviors, at the user-crowd level, we propose aggregating user cliques into synthesized users with rich behaviors for more comprehensive LLM-driven multi-interest analysis. We formulate a max covering problem to ensure the compactness and representativeness of synthesized users' behaviors, and then conduct contrastive learning based on their LLM-driven multi-interests to disentangle item representations among different interests. Experiments on real-world datasets show the superiority of our approach against state-of-the-art methods.

Related papers

• Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model [20.79990807882704]
  We propose a Hierarchical Tree Search-based User Lifelong Behavior Modeling framework (HiT-LBM)<n>HiT-LBM integrates Chunked User Behavior Extraction (CUBE) and Hierarchical Tree Search for Interest (HTS) to capture diverse interests and interest evolution of user.<n>We also design Temporal-Ware Interest Fusion (TIF) to integrate interests from multiple behavior chunks, constructing a comprehensive representation of user lifelong interests.
  arXiv  Detail & Related papers  (2025-05-26T04:32:57Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs [40.38930402847949]
  We propose an agent-centric personalized clustering framework.<n>Agents traverse a relational graph to search for clusters based on user interests.<n>Results show that the proposed method achieves NMI scores of 0.9667 and 0.9481 on the Card Order and Card Suits benchmarks.
  arXiv  Detail & Related papers  (2025-03-28T08:45:15Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• LIBER: Lifelong User Behavior Modeling Based on Large Language Models [42.045535303737694]
  We propose Lifelong User Behavior Modeling (LIBER) based on large language models. LIBER has been deployed on Huawei's music recommendation service and achieved substantial improvements in users' play count and play time by 3.01% and 7.69%.
  arXiv  Detail & Related papers  (2024-11-22T03:43:41Z)
• LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation [54.396000434574454]
  We propose a novel multi-interest SR framework combining implicit behavioral and explicit semantic perspectives.<n>It includes two modules: the Implicit Behavioral Interest Module and the Explicit Semantic Interest Module.<n>Experiments on four real-world datasets validate the framework's effectiveness and practicality.
  arXiv  Detail & Related papers  (2024-11-14T13:00:23Z)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align''<n>We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures.<n>For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation [58.04939553630209]
  In real-world systems, most users interact with only a handful of items, while the majority of items are seldom consumed. These two issues, known as the long-tail user and long-tail item challenges, often pose difficulties for existing Sequential Recommendation systems. We propose the Large Language Models Enhancement framework for Sequential Recommendation (LLM-ESR) to address these challenges.
  arXiv  Detail & Related papers  (2024-05-31T07:24:42Z)
• Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering [8.447067012487866]
  Multi-MaP is a novel method employing a multi-modal proxy learning process. It captures a user's interest via a keyword but also facilitates identifying relevant clusterings. Our experiments show that Multi-MaP consistently outperforms state-of-the-art methods in all benchmark multi-clustering vision tasks.
  arXiv  Detail & Related papers  (2024-04-24T05:20:42Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation [52.89816309759537]
  Multi-types of behaviors (e.g., clicking, adding to cart, purchasing, etc.) widely exist in most real-world recommendation scenarios. The state-of-the-art multi-behavior models learn behavior dependencies indistinguishably with all historical interactions as input. We propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning framework to learn shared and behavior-specific interests for different behaviors.
  arXiv  Detail & Related papers  (2022-08-03T05:28:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.