{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","arxiv_id":"2403.02130","date":"2024-03-04","proceeding":null,"authors":["Alexander Brinkmann","Nick Baumann","Christian Bizer"],"abstract":"Product offers on e-commerce websites often consist of a product title and a textual product description. In order to enable features such as faceted product search or to generate product comparison tables, it is necessary to extract structured attribute-value pairs from the unstructured product titles and descriptions and to normalize the extracted values to a single, unified scale for each attribute. This paper explores the potential of using large language models (LLMs), such as GPT-3.5 and GPT-4, to extract and normalize attribute values from product titles and descriptions. We experiment with different zero-shot and few-shot prompt templates for instructing LLMs to extract and normalize attribute-value pairs. We introduce the Web Data Commons - Product Attribute Value Extraction (WDC-PAVE) benchmark dataset for our experiments. WDC-PAVE consists of product offers from 59 different websites which provide schema.org annotations. The offers belong to five different product categories, each with a specific set of attributes. The dataset provides manually verified attribute-value pairs in two forms: (i) directly extracted values and (ii) normalized attribute values. The normalization of the attribute values requires systems to perform the following types of operations: name expansion, generalization, unit of measurement conversion, and string wrangling. Our experiments demonstrate that GPT-4 outperforms the PLM-based extraction methods SU-OpenTag, AVEQA, and MAVEQA by 10%, achieving an F1-score of 91%. For the extraction and normalization of product attribute values, GPT-4 achieves a similar performance to the extraction scenario, while being particularly strong at string wrangling and name expansion.","url_abs":"https://arxiv.org/abs/2403.02130v4","url_pdf":"https://arxiv.org/pdf/2403.02130v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"using-llms-for-the-extraction-and","repo_url":"https://github.com/wbsg-uni-mannheim/wdc-pave","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"attribute-value-extraction","task_name":"Attribute Value Extraction"},{"task_slug":"product-recommendation","task_name":"Product Recommendation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"wdc-pave","name":"WDC-PAVE","full_name":"Web Data Commones - Product Attribute Value Extraction"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset":"WDC-PAVE","model":"GPT-4_10_example_values_&_10_demonstrations","rank_in_archive_order":1,"of":5,"metrics":{"F1-Score":"90.54"},"uses_additional_data":false},{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset":"WDC-PAVE","model":"GPT-3.5_10_example_values_&_10_demonstrations","rank_in_archive_order":2,"of":5,"metrics":{"F1-Score":"88.02"},"uses_additional_data":false},{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset":"WDC-PAVE","model":"AVEQA","rank_in_archive_order":3,"of":5,"metrics":{"F1-Score":"80.83"},"uses_additional_data":false},{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset":"WDC-PAVE","model":"MAVEQA","rank_in_archive_order":4,"of":5,"metrics":{"F1-Score":"65.10"},"uses_additional_data":false},{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset":"WDC-PAVE","model":"SU-OpenTag","rank_in_archive_order":5,"of":5,"metrics":{"F1-Score":"60.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.02130","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}