LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation

TL;DR

This paper introduces a novel LLM-based bi-level multi-interest framework for sequential recommendation that combines behavioral data and semantic insights, improving accuracy while maintaining efficiency.

Contribution

It proposes a dual-module framework integrating LLM-driven semantic interest extraction with traditional behavioral modeling for enhanced sequential recommendation.

Findings

Outperforms existing models on four real-world datasets.

Effectively combines implicit behavioral and explicit semantic interests.

Maintains efficiency by using only IBIM during inference.

Abstract

Sequential recommendation (SR) leverages users' dynamic preferences, with recent advances incorporating multi-interest learning to model diverse user interests. However, most multi-interest SR models rely on noisy, sparse implicit feedback, limiting recommendation accuracy. Large language models (LLMs) offer robust reasoning on low-quality data but face high computational costs and latency challenges for SR integration. We propose a novel LLM-based multi-interest SR framework combining implicit behavioral and explicit semantic perspectives. It includes two modules: the Implicit Behavioral Interest Module (IBIM), which learns from user behavior using a traditional SR model, and the Explicit Semantic Interest Module (ESIM), which uses clustering and prompt-engineered LLMs to extract semantic multi-interest representations from informative samples. Semantic insights from ESIM enhance IBIM's behavioral representations via modality alignment and semantic prediction tasks. During inference, only IBIM is used, ensuring efficient, LLM-free recommendations. Experiments on four real-world datasets validate the framework's effectiveness and practicality.