# ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction

arXiv: https://arxiv.org/abs/2310.12537 · HTML: https://mlsanity.com/paper/2310.12537/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 55 references that are in the map.
- First posted on arXiv 19 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Look at the First Sentence: Position Bias in Question Answering](https://mlsanity.com/paper/2004.14602/) (2020)
- [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)
- [Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product](https://mlsanity.com/paper/2009.07162/) (2020)
- [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)
- [Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text](https://mlsanity.com/paper/2305.08804/) (2023)
- [QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction](https://mlsanity.com/paper/2108.08468/) (2021)
- [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)

- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [Using LLMs for the Extraction and Normalization of Product Attribute Values](https://mlsanity.com/paper/2403.02130/) (2024)
- [A survey on fairness of large language models in e-commerce: progress, application, and challenge](https://mlsanity.com/paper/2405.13025/) (2024)
- [ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2502.20196/) (2025)
- [LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models](https://mlsanity.com/paper/2504.00752/) (2025)
- [eC-Tab2Text: Aspect-Based Text Generation from e-Commerce Product Tables](https://mlsanity.com/paper/2502.14820/) (2025)
- [MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction](https://mlsanity.com/paper/2510.05611/) (2025)
- [Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes](https://mlsanity.com/paper/2507.01810/) (2025)
- [AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction](https://mlsanity.com/paper/2604.16950/) (2026)
- [Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction](https://mlsanity.com/paper/2604.26209/) (2026)
- [Intra-Prompt Parallel Decoding for Common-Context Question Answering](https://mlsanity.com/paper/2609.05707/) (2026)
- [A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification](https://mlsanity.com/paper/2405.10918/) (2024)
- [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)
- [SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction](https://mlsanity.com/paper/2607.00008/) (2026)
- [TRACE: Agentic Catalog Enrichment with Multi-source Evidence Grounding](https://mlsanity.com/paper/2608.20844/) (2026)
- [DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction](https://mlsanity.com/paper/2608.22014/) (2026)
- [HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning](https://mlsanity.com/paper/2608.24467/) (2026)
- [MERIT: Mitigating Exposure Bias in Generative XMC for User-Interest Propensity Modeling](https://mlsanity.com/paper/2608.28931/) (2026)
- [Scaling E-Commerce Attribute Extraction with Parallel Decoding](https://mlsanity.com/paper/2609.09716/) (2026)
- [Resolving the Missing Financial Data Crisis: A Generative AI Pipeline for SEC 10-K Extraction](https://mlsanity.com/paper/2609.35864/) (2026)

## Abstract (arXiv)

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.