Author(s): Luedecke, Linus
Date: 2025
Persistent ID: http://hdl.handle.net/10362/181471
Origin: Repositório Institucional da UNL
Subject(s): Large Language Models; Hierarchical classification; E-Commerce; In-context learning; Fine tuning; Prompt engineering; Knowledge graphs; Retrieval Augmented Generation; Entity matching
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 var ious scenarios. 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.
