用大模型提升会话推荐，解决上下文少、效率低问题
SPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-based Recommendation
- 构建全局意图池约束大模型，减少错误推测
- 仅对不确定会话调用大模型，推理速度更快
- 推荐更可解释，适合需要透明性的场景
大型语言模型（LLMs）通过用户行为生成文本画像，提升了传统推荐模型的效果。然而，直接应用于会话推荐（SBR）仍面临严重会话上下文稀缺和扩展性差的问题。本文提出SPRINT框架，在保证高效训练与推理的前提下，引入可靠且信息丰富的用户意图。SPRINT通过全局意图池约束大模型画像，并基于推荐性能验证推断出的意图，以缓解有限上下文下的噪声与幻觉问题。为确保可扩展性，训练时仅对不确定会话调用大模型，推理时由轻量级意图预测器统一处理所有会话，无需依赖大模型。在真实数据集上的实验表明，SPRINT持续优于当前最优方法，同时提供更具可解释性的推荐结果。
原文摘要 · Abstract (English)
Large language models (LLMs) have enhanced conventional recommendation models via user profiling, which generates representative textual profiles from users' historical interactions. However, their direct application to session-based recommendation (SBR) remains challenging due to severe session context scarcity and poor scalability. In this paper, we propose SPRINT, a scalable SBR framework that incorporates reliable and informative intents while ensuring high efficiency in both training and inference. SPRINT constrains LLM-based profiling with a global intent pool and validates inferred intents based on recommendation performance to mitigate noise and hallucinations under limited context. To ensure scalability, LLMs are selectively invoked only for uncertain sessions during training, while a lightweight intent predictor generalizes intent prediction to all sessions without LLM dependency at inference time. Experiments on real-world datasets show that SPRINT consistently outperforms state-of-the-art methods while providing more explainable recommendations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。