Publicação
Enhancing product categorization with LLMs: fine-tuning decoder-only language models for hierarchical e-commerce product classification: a causal language modeling approach
| datacite.subject.fos | Ciências Sociais::Economia e Gestão | |
| dc.contributor.advisor | Han, Qiwei | |
| dc.contributor.author | Białczyk, Kuba Maciej | |
| dc.date.accessioned | 2026-04-07T08:57:29Z | |
| dc.date.available | 2026-04-07T08:57:29Z | |
| dc.date.issued | 2025-01-22 | |
| dc.date.submitted | 2025-01-22 | |
| dc.description.abstract | This research explored techniques to improve Large Language Models performance for Hierarchical Product Classification (HPC), including optimized fine-tuning, optimal prompting techniques, taxonomy-specific Knowledge Graphs, leveraging Retrieval-Augmented Generation, 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. | eng |
| dc.identifier.tid | 204134110 | |
| dc.identifier.uri | http://hdl.handle.net/10362/202068 | |
| dc.language.iso | eng | |
| dc.relation | UID/ECO/00124/2013 | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | Large language models | |
| dc.subject | Hierarchical classification | |
| dc.subject | E-Commerce | |
| dc.subject | In-context learning | |
| dc.subject | Fine tuning | |
| dc.subject | Prompt engineering | |
| dc.subject | Knowledge graphs | |
| dc.subject | Retrieval augmented generation | |
| dc.subject | Entity matching | |
| dc.title | Enhancing product categorization with LLMs: fine-tuning decoder-only language models for hierarchical e-commerce product classification: a causal language modeling approach | eng |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| thesis.degree.name | A Work Project, presented as part of the requirements for the Award of a Master’s Degree in Business Analytics from the Nova School of Business and Economics |