Session-Based Recommendation with Validated and Enriched LLM Intents

2025-08-01

AI Summary

To address data sparsity in session-based recommendation (SBR) caused by session brevity and user anonymity, this paper proposes an LLM-driven two-stage intent enhancement framework. Methodologically: (1) a prediction–correction loop dynamically validates and refines LLM-generated user intents; (2) a global intent pool constrains the output space, coupled with a lightweight multi-intent prediction and fusion module; (3) cross-session behavioral similarity is leveraged to compensate for LLM intent generation failures, enhancing robustness. The work makes three key contributions: it is the first to systematically tackle intent quality verification, multi-intent integration, and failure compensation in LLM-based intent generation for SBR. Extensive experiments demonstrate significant improvements over state-of-the-art methods across multiple benchmarks, achieving higher recommendation accuracy and enhanced interpretability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Session-based recommendation (SBR) aims to predict the next item for an anonymous user in a timely manner. However, SBR suffers from data sparsity due to the short and anonymous nature of sessions. Recently, an emerging line of work has explored inferring the underlying user intents of a session using large language models (LLMs), with the generated intents serving as auxiliary training signals to enhance SBR models. Despite its promise, this approach faces three key challenges: validating intent quality, incorporating session-level multi-intents, and complementing inevitable LLM failure cases. In this paper, we propose VELI4SBR, a two-stage framework that leverages Validated and Enriched LLM-generated Intents for SBR. In the first stage, we generate high-quality intents using a predict-and-correct loop that validates the informativeness of LLM-generated intents with a global intent pool to constrain the LLM's output space and reduce hallucination. In the second stage, we enhance the SBR model using the generated intents through a lightweight multi-intent prediction and fusion mechanism. Furthermore, we introduce a training strategy that compensates for LLM failures by inferring intents from inter-session behavioral similarities. Extensive experiments show that VELI4SBR outperforms state-of-the-art baselines while improving explainability.

Problem

• Validating quality of LLM-generated user intents
• Incorporating multi-intents at session level
• Compensating for inevitable LLM failure cases

Innovation

• Predict-and-correct loop validates LLM intent quality
• Multi-intent fusion enhances session-based recommendations
• Inter-session similarity compensates for LLM failures