# Using LLMs for the Extraction and Normalization of Product Attribute Values

arXiv: https://arxiv.org/abs/2403.02130 · HTML: https://mlsanity.com/paper/2403.02130/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [LLMs Accelerate Annotation for Medical Information Extraction](https://mlsanity.com/paper/2312.02296/) (2023)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]](https://mlsanity.com/paper/1806.01264/) (2018)
- [MAVE: A Product Dataset for Multi-source Attribute Value Extraction](https://mlsanity.com/paper/2112.08663/) (2021)
- [LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction](https://mlsanity.com/paper/2403.00863/) (2024)
- [AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding](https://mlsanity.com/paper/2106.02318/) (2021)
- [GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles](https://mlsanity.com/paper/2205.12505/) (2022)
- [OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision](https://mlsanity.com/paper/2204.13874/) (2022)
- [ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction](https://mlsanity.com/paper/2310.12537/) (2023)
- [Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction](https://mlsanity.com/paper/2206.14264/) (2022)

## Built on by (most cited first, 20 of 20)

- [LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs](https://mlsanity.com/paper/2408.08656/) (2024)
- [ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2502.20196/) (2025)
- [TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification](https://mlsanity.com/paper/2501.03835/) (2025)
- [EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction](https://mlsanity.com/paper/2406.06839/) (2024)
- [Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs](https://mlsanity.com/paper/2510.23941/) (2025)
- [Exploring Large Language Models for Product Attribute Value Identification](https://mlsanity.com/paper/2409.12695/) (2024)
- [Visual Zero-Shot E-Commerce Product Attribute Value Extraction](https://mlsanity.com/paper/2502.15979/) (2025)
- [Automatic Prompt Optimization for Dataset-Level Feature Discovery](https://mlsanity.com/paper/2601.13922/) (2026)
- [Automatic End-to-End Data Integration using Large Language Models](https://mlsanity.com/paper/2603.10547/) (2026)
- [Self-Refinement Strategies for LLM-based Product Attribute Value Extraction](https://mlsanity.com/paper/2501.01237/) (2025)
- [NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction](https://mlsanity.com/paper/2505.17125/) (2025)
- [VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models](https://mlsanity.com/paper/2508.11801/) (2025)
- [Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction](https://mlsanity.com/paper/2604.26209/) (2026)
- [Where Do Your Citations Come From? Citation-Constellation: A Free, Open-Source, No-Code, and Auditable Tool for Citation Network Decomposition with Complementary BARON and HEROCON Scores](https://mlsanity.com/paper/2603.24216/) (2026)
- [Method for Aggregating Unstructured Data Using Large Language Models](https://mlsanity.com/paper/2604.16425/) (2026)
- [AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach](https://mlsanity.com/paper/2606.24655/) (2026)
- [JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications](https://mlsanity.com/paper/2606.28070/) (2026)
- [Enhancing Generative Information Extraction with Two-step Validation: A Product Attribute Use Case](https://mlsanity.com/paper/2607.26780/) (2026)
- [DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction](https://mlsanity.com/paper/2608.22014/) (2026)
- [Positional task conditioning for scalable defect detection across product families in large product catalogs](https://mlsanity.com/paper/2609.09567/) (2026)

## Abstract (arXiv)

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.