Enhancing product categorization with retrieval augmented generation: a comparative study of architectures, techniques and strategies
Year: 2025
Type: dissertation
Abstract: This research explored techniques to improve Large Language Models performance for Hi erarchical Product Classification (HPC), including optimized fine-tuning, optimal prompting techniques, taxonomy-specific Knowledge Graphs, leveraging Retrieval-Augmented Genera tion, and implementing LLM-based Entity Matching. Tested on benchmark datasets Icecat and WDC-222, these methods significantly enhanced LLMs’ ability to solve HPC tasks across various scenarios. The paper investigates the enhancement of product categorization through various RAG configurations such as NaiveRAG, AdvancedRAG, GraphRAG, and HybridRAG, applied in both flat and hierarchical systems. Results achieved a hierarchical F1-score (hF) of 0.921, surpassing traditional DL benchmarks (0.85 hF). While not outperforming proprietary models like GPT, the proposed approaches offer a cost-efficient and effective alternative for businesses, demonstrating strong performance without reliance on expensive LLM solutions.
Author: Marrero, Rafael Alejandro Moles
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7000245496