Papers › ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute...
ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
Alexander Brinkmann, Roee Shraga, Christian Bizer
E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product descriptions, necessitating the extraction of attribute-value pairs from these texts. BERT-based extraction methods require large amounts of task-specific training data and struggle with unseen attribute values. This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative. We propose prompt templates for zero-shot and few-shot scenarios, comparing textual and JSON-based target schema representations. Our experiments show that GPT-4 achieves the highest average F1-score of 85% using detailed attribute descriptions and demonstrations. Llama-3-70B performs nearly as well, offering a competitive open-source alternative. GPT-4 surpasses the best PLM baseline by 5% in F1-score. Fine-tuning GPT-3.5 increases the performance to the level of GPT-4 but reduces the model's ability to generalize to unseen attribute values.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Attribute Value Extraction | AE-110k | GPT-4-json-val-10-dem | F1-score | 87.5 | #1 of 2 | Archive leaderboard | report |
| Attribute Value Extraction | AE-110k | ft-GPT-3.5-json-val | F1-score | 86 | #2 of 2 | Archive leaderboard | report |
| Attribute Value Extraction | OA-Mine - annotations | ft-GPT-3.5-json-val | F1-score | 84.5 | #1 of 2 | Archive leaderboard | report |
| Attribute Value Extraction | OA-Mine - annotations | GPT-4-json-val-10-dem | F1-score | 82.2 | #2 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections