Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
- 10.
- 11.
References
Brinkmann, A., Baumann, N., Bizer, C.: Using LLMs for the extraction and normalization of product attribute values. In: ADBIS, pp. 217–230 (2024)
Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. In: NeurIPS, vol. 33, pp. 1877–1901 (2020)
Chen, W.T., Shinzato, K., Yoshinaga, N., et al.: Does named entity recognition truly not scale up to real-world product attribute extraction? In: EMNLP, pp. 152–159 (2023)
Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171–4186 (2019)
Dubey, A., Jauhri, A., Pandey, A., et al.: The LLaMA 3 herd of models (2024). arXiv:2407.21783 [cs]
Fang, C., Li, X., Fan, Z., et al.: LLM-Ensemble: optimal large language model ensemble method for e-commerce product attribute value extraction (2024). arXiv:2403.00863 [cs]
Ghani, R., Probst, K., Liu, Y., et al.: Text mining for product attribute extraction. In: ACM SIGKDD Explorations Newsletter, vol. 8, pp. 41–48 (2006)
Goel, A., Gueta, A., Gilon, O., et al.: LLMs accelerate annotation for medical information extraction. In: ML4H, pp. 82–100 (2023)
Khorashadizadeh, H., Mihindukulasooriya, N., Tiwari, S., et al.: Exploring in-context learning capabilities of foundation models for generating knowledge graphs from text. In: TEXT2KG | BiKE, vol. 3447, pp. 132–153 (2023)
OpenAI: GPT-4 technical report (2023). arXiv:2303.08774 [cs]
Ouyang, L., Wu, J., Jiang, X.: Training language models to follow instructions with human feedback. In: NeurIPS, vol. 35, pp. 27730–27744 (2022)
Parekh, T., Hsu, I.H., Huang, K.H., et al.: GENEVA: benchmarking generalizability for event argument extraction with hundreds of event types and argument roles. In: ACL, pp. 3664–3686 (2023)
Putthividhya, D., Hu, J.: Bootstrapped named entity recognition for product attribute extraction. In: EMNLP, pp. 1557–1567 (2011)
Ren, Z., He, X., Yin, D., et al.: Information discovery in e-commerce: half-day SIGIR 2018 tutorial. In: SIGIR, pp. 1379–1382 (2018)
Shinzato, K., Yoshinaga, N., Xia, Y., et al.: Simple and effective knowledge-driven query expansion for QA-based product attribute extraction. In: ACL, pp. 227–234 (2022)
Vandic, D., van Dam, J.W., Frasincar, F.: Faceted product search powered by the Semantic Web. Decis. Support Syst. 53(3), 425–437 (2012)
Wang, Q., Yang, L., Kanagal, B., et al.: Learning to extract attribute value from product via question answering: a multi-task approach. In: SIGKDD, pp. 47–55 (2020)
Wang, Q., Yang, L., Wang, J., et al.: SMARTAVE: structured multimodal transformer for product attribute value extraction. In: EMNLP, pp. 263 – 276 (2022)
Wang, X., Li, S., Ji, H.: Code4Struct: code generation for few-shot event structure prediction. In: ACL, vol. 1, pp. 3640–3663 (2023)
Wei, J., Tay, Y., Bommasani, R., et al.: Emergent abilities of large language models. TMLR (2022)
Wong, Y.W., Widdows, D., Lokovic, T., et al.: Scalable attribute-value extraction from semi-structured text. In: ICDMW, pp. 302–307 (2009)
Xu, H., Wang, W., Mao, X., et al.: Scaling up open tagging from tens to thousands: comprehension empowered attribute value extraction from product title. In: ACL, pp. 5214–5223 (2019)
Yan, J., Zalmout, N., Liang, Y., et al.: AdaTag: multi-attribute value extraction from product profiles with adaptive decoding. In: ACL|IJCNLP, pp. 4694–4705 (2021)
Yang, L., Wang, Q., Wang, J., et al.: MixPAVE: mix-prompt tuning for few-shot product attribute value extraction. In: ACL, pp. 9978–9991 (2023)
Yang, L., Wang, Q., Yu, Z., et al.: MAVE: a product dataset for multi-source attribute value extraction. In: WSDM, pp. 1256–1265 (2022)
Zamfirescu-Pereira, J., Wong, R.Y., Hartmann, B., et al.: Why johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts. In: CHI, pp. 1–21 (2023)
Zhang, L., Zhu, M., Huang, W.: A framework for an ontology-based e-commerce product information retrieval system. JCP 4(6), 436–443 (2009)
Zhang, X., Zhang, C., Li, X., et al.: OA-Mine: open-world attribute mining for e-commerce products with weak supervision. In: WWW, pp. 3153–3161 (2022)
Zheng, G., Mukherjee, S., Dong, X.L., et al.: OpenTag: open attribute value extraction from product profiles. In: SIGKDD, pp. 1049–1058 (2018)
Zhu, T., Wang, Y., Li, H., et al.: Multimodal joint attribute prediction and value extraction for E-commerce product. In: EMNLP, pp. 2129–2139 (2020)
Zou, H.P., Samuel, V., Zhou, Y., et al.: ImplicitAVE: an open-source dataset and multimodal LLMs benchmark for implicit attribute value extraction (2024). arXiv:2404.15592 [cs]
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Brinkmann, A., Shraga, R., Bizer, C. (2025). ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction. In: Delir Haghighi, P., Greguš, M., Kotsis, G., Khalil, I. (eds) Information Integration and Web Intelligence. iiWAS 2024. Lecture Notes in Computer Science, vol 15342. Springer, Cham. https://doi.org/10.1007/978-3-031-78090-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-78090-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78089-9
Online ISBN: 978-3-031-78090-5
eBook Packages: Computer ScienceComputer Science (R0)