AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Murilo Gazzola, Hugo Gobato Souto, Samuel Silva, Júlia Schubert Peixoto, Felipe Siqueira, André Luis Pedroso de Morais, Caio Gomes
• Venue: arXiv: cs.CL
• Published: 2026-06-23
• Collected: 2026-06-24
• URL: http://arxiv.org/abs/2606.24655v1
• PDF: https://arxiv.org/pdf/2606.24655v1
• DOI: 10.5753/stil.2025.37821

Plain-Language Brief

The paper introduces AI-PAVEBr, a system that uses Large Language Models (LLMs) to extract product attributes in Portuguese e-commerce catalogs more accurately than traditional methods. The authors also present a new dataset for PAVE research called the Golden Set, which is manually annotated and publicly available.

What the Document Says

• The paper focuses on improving Product Attribute Value Extraction (PAVE) in the Brazilian e-commerce market due to the complexity of product data and linguistic nuances in Portuguese.
• AI-PAVEBr is introduced, a system using LLMs for high-accuracy PAVE specific to Brazilian e-commerce catalogs.
• The Golden Set is introduced as a new, manually annotated dataset for PAVE research in Portuguese.
• Details about the creation process and structure (Entity, Category, Subcategories) of the Golden Set are provided.
• Experiments show that AI-PAVE-Br outperforms conventional Named Entity Recognition (NER) baselines.

Key Concepts Mentioned

• Product Attribute Value Extraction (PAVE)
• Large Language Models (LLMs)
• Brazilian e-commerce
• Named Entity Recognition (NER)
• Golden Set

Claims Made by the Document

• AI-PAVEBr outperforms conventional Named Entity Recognition baselines.

Evidence Used

• Our experiments conclusively show that AI-PAVE-Br...outperforms conventional Named Entity Recognition (NER) baselines.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The explosive growth and complexity of product data within the dynamic Brazilian e-commerce landscape demand robust and specialized methods for structured information extraction. Traditional approaches to Product Attribute Value Extraction (PAVE) often struggle with the linguistic nuances and sheer diversity of product descriptions in Portuguese. To address this critical gap, this paper introduces two major contributions. First, we present AI-PAVEBr, a specialized system engineered with Large Language Models (LLMs) to perform high-accuracy PAVE specifically for Brazilian e-commerce catalogs. Second, to facilitate reproducible research and provide a definitive benchmark, we introduce and share the Golden Set, a new, meticulously curated, and manually annotated dataset for PAVE in Portuguese. We detail the creation process and structure (Entity, Category, Subcategories) of this high-quality reference set. Our experiments conclusively show that AI-PAVE-Br, leveraging targeted prompt engineering, dramatically outperforms conventional Named Entity Recognition (NER) baselines. This work not only delivers a superior, scalable solution for a major non-English market but also enriches the NLP community with a valuable, publicly available resource for future PAVE research.