Taxonomy-Guided Zero-Shot Recommendations with LLMs

TL;DR

This paper introduces TaxRec, a taxonomy-guided method that improves zero-shot recommendations with large language models by organizing item information, optimizing prompts, and controlling generation, resulting in more accurate and relevant suggestions.

Contribution

The paper presents a novel taxonomy-based framework for zero-shot recommendation with LLMs, addressing prompt length and unstructured data issues without domain-specific fine-tuning.

Findings

Significant improvement in recommendation quality over traditional zero-shot methods

Effective use of taxonomy dictionaries for structured item categorization

Enhanced prompt efficiency and recommendation relevance

Abstract

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.