A Chain-of-Thought Approach to Semantic Query Categorization in e-Commerce Taxonomies
This work addresses the challenge of accurately mapping user queries to leaf categories in e-commerce search by introducing, for the first time, the Chain-of-Thought (CoT) paradigm to hierarchical category classification. The proposed method integrates tree search with semantic scoring from large language models (LLMs) in a lightweight framework that not only improves classification accuracy but also effectively narrows the candidate product scope, enhances multi-intent understanding, and reveals structural flaws in the category taxonomy. Experimental results demonstrate that the CoT-based approach significantly outperforms embedding-based baselines on both human-annotated datasets and relevance evaluations, while scaling efficiently to handle millions of queries.