阿里速卖通用语义指令生成多任务推荐，更懂用户真实需求。
SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress
- 将商品实体统一嵌入语义与协同信号融合空间，支持精准建模。
- 构建大规模指令微调数据集，实现多种推荐任务的灵活响应。
- 三步生成+自适应融合机制，兼顾推荐准确率与多样性。
随着大语言模型的快速发展，生成式推荐正重塑推荐系统范式。然而，现有方法仍局限于交互驱动的下一步物品预测，难以跟上最新趋势或满足真实场景中多样化的推荐任务和业务需求。为此，我们提出SIGMA——部署于速卖通的语义基底指令驱动生成式多任务推荐系统。首先，将商品实体嵌入统一潜在空间，捕捉通用语义与协同信号；在此基础上，设计混合商品标记化方法，实现精确建模与高效生成。此外，构建大规模多任务监督微调数据集，使SIGMA可通过指令遵循完成各类推荐任务。最后，设计三步物品生成流程，并引入自适应概率融合机制，根据任务需求校准输出分布，提升推荐准确率与多样性。大量离线实验与在线A/B测试验证了SIGMA在多种实际推荐任务中的有效性。
原文摘要 · Abstract (English)
With the rapid evolution of Large Language Models (LLMs), generative recommendation is gradually reshaping the paradigm of recommender systems. However, most existing methods remain confined to the interaction-driven next-item prediction paradigm, struggling to keep pace with the latest evolving trends or address the diverse recommendation tasks along with business-specific requirements in real-world scenarios. To this end, we present SIGMA, a Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender deployed at AliExpress. Specifically, we first ground item entities in a unified latent space capturing both general semantics and collaborative signals. Building upon this, we introduce a hybrid item tokenization method for both precise modeling and efficient generation. Moreover, we construct a large-scale multi-task supervised fine-tuning dataset empowering SIGMA to fulfill various recommendation demands via instruction-following. Finally, we design a three-step item generation procedure integrated with an adaptive probabilistic fusion mechanism to calibrate the output distributions based on task-specific requirements for recommendation accuracy and diversity. Extensive offline experiments and online A/B tests demonstrate the effectiveness of SIGMA across various real-world recommendation tasks.
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。