GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models

GrocLM：基于大语言模型的电子商务杂货类别推荐

Abstract: The rapid growth of online grocery shopping requires recommendation systems that capture cyclical purchasing behavior and diverse user intents. Traditional item-level methods face scalability and accuracy challenges, motivating category-level recommendation as a more structured and practical alternative.

摘要： 在线杂货购物的快速增长要求推荐系统能够捕捉周期性的购买行为和多样化的用户意图。传统的基于物品（item-level）的方法在可扩展性和准确性方面面临挑战，这促使人们转向基于类别（category-level）的推荐，将其作为一种更结构化且实用的替代方案。

We present GROCLM, a fine-tuned language model for grocery category recommendation in a real-world production environment. GROCLM employs a two-stage LoRA-based training strategy to encode cyclical purchasing patterns directly into model parameters, enabling more effective utilization of rebuying signals compared to prompt-based conditioning.

我们提出了 GROCLM，这是一个针对真实生产环境下的杂货类别推荐而微调的语言模型。GROCLM 采用了一种基于 LoRA 的两阶段训练策略，将周期性购买模式直接编码到模型参数中，与基于提示词（prompt-based）的条件化方法相比，能够更有效地利用复购信号。

To ensure valid and controllable outputs, we further introduce a trie-based constrained decoding mechanism over a predefined category space. Experiments on both proprietary production data and a public benchmark demonstrate that GROCLM consistently outperforms strong baselines.

为了确保输出的有效性和可控性，我们进一步引入了一种基于前缀树（trie-based）的约束解码机制，该机制作用于预定义的类别空间。在专有生产数据和公开基准测试上的实验表明，GROCLM 的表现始终优于强基准模型。

In a live production restocking task, GROCLM achieves a 7.5% relative improvement in cart-adds per impression, while maintaining efficient inference by generating all categories jointly. These results highlight the effectiveness and practicality of integrating large language models into structured recommendation systems.

在实际生产环境的补货任务中，GROCLM 在每次展示的加购率（cart-adds per impression）上实现了 7.5% 的相对提升，同时通过联合生成所有类别保持了高效的推理速度。这些结果凸显了将大语言模型集成到结构化推荐系统中的有效性和实用性。