With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of item information. By incorporating the taxonomy dictionary into LLM prompts, we achieve efficient token utilization and controlled feature generation, leading to more accurate and contextually relevant recommendations. Our Taxonomy-guided Recommendation (TaxRec) approach features a two-step process: one-time taxonomy categorization and LLM-based recommendation, enabling zero-shot recommendations without the need for domain-specific fine-tuning. Experimental results demonstrate TaxRec significantly enhances recommendation quality compared to traditional zero-shot approaches, showcasing its efficacy as personal recommender with LLMs. Code is available at https://github.com/yueqingliang1/TaxRec.

翻译：随着大语言模型（LLMs）的出现及其执行多样化任务的能力，它们在推荐系统（RecSys）中的应用展现出广阔前景。然而，将LLMs部署到推荐系统中时，我们面临着显著挑战，例如有限的提示长度、非结构化的项目信息以及无约束的推荐生成，导致性能欠佳。为解决这些问题，我们提出了一种使用分类词典的新方法。该方法为项目的分类与组织提供了系统化框架，提升了项目信息的清晰度与结构化程度。通过将分类词典整合到LLM提示中，我们实现了高效的令牌利用和受控的特征生成，从而产生更准确且与上下文相关的推荐。我们的分类引导推荐（TaxRec）方法采用两步流程：一次性分类归类和基于LLM的推荐，无需领域特定微调即可实现零样本推荐。实验结果表明，与传统零样本方法相比，TaxRec显著提升了推荐质量，证明了其作为基于LLM的个性化推荐系统的有效性。代码发布于 https://github.com/yueqingliang1/TaxRec。