用多模态大模型挖掘用户深层兴趣，提升推荐系统个性化与可解释性。
DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation
- 通过结构化提示和多大模型协作，挖掘用户潜在深层兴趣
- 在三个亚马逊数据集上，点击率与排序指标提升超8%，跨领域泛化能力提高24.8%
- 适合关注推荐系统可解释性与深度用户建模的研究者
我们提出 DeepInterestGR，一个将深层兴趣挖掘融入生成式推荐流程的新框架。该方法解决现有生成式推荐依赖表层文本特征、难以捕捉用户潜在动机的“浅层兴趣”问题，限制了个性化深度与可解释性。通过结构化推理提示实现多大模型兴趣挖掘（MLIM），利用带奖励标注的深度兴趣机制（RLDI）保证质量，并基于RQ-VAE进行兴趣增强型物品离散化（IEID），结合两阶段SFT-GRPO训练流程，在兴趣感知奖励引导下优化。在Beauty、Sports、Instruments三个Amazon Review基准上验证，对比14种先进基线（如SASRec、BERT4Rec、TIGER、LC-Rec、S-DPO），HR@10相对提升5.8%-8.3%，NDCG@10提升7.7%-9.9%，跨域泛化性能提升24.8%。结果表明，融合深层语义兴趣能有效提升基于SID的生成式推荐效果。
原文摘要 · Abstract (English)
We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem - existing generative methods rely on surface-level textual features and fail to capture latent user motivations, limiting personalization depth and recommendation interpretability. Our approach leverages Multi-LLM Interest Mining (MLIM) via structured reasoning prompting, Reward-Labeled Deep Interest (RLDI) for quality control, and Interest-Enhanced Item Discretization (IEID) via RQ-VAE, combined with a two-stage SFT-GRPO training pipeline guided by an Interest-Aware Reward. We validate DeepInterestGR on three Amazon Review benchmarks (Beauty, Sports, Instruments), comparing against 14 state-of-the-art baselines including SASRec, BERT4Rec, TIGER, LC-Rec, and S-DPO. Our method achieves 5.8%-8.3% relative improvements on HR@10 and 7.7%-9.9% on NDCG@10 over the strongest baseline, with cross-domain generalization gains of +24.8%. These results provide evidence that incorporating deep semantic interests can effectively improve SID-based generative recommendation.
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。