The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
LLMs for product classification in e-commerce: A zero-shot comparative study of GPT and claude models
Open accessAbstract
In the rapidly evolving e-commerce landscape, efficient and accurate product classification is essential for enhancing customer experience and streamlining operations. Traditional product classification methods, which depend heavily on labeled data and manual effort, struggle with scalability and adaptability to diverse product categories. This study explores the transformative potential of large language models (LLMs) for zero-shot product classification in e-commerce, addressing the challenge of automating product categorization without prior labeled training data. We evaluate the performance of four state-of-the-art LLMs — GPT-4o, GPT-4o mini, Claude 3.5 Sonnet, and Claude 3.5 Haiku — on a diverse dataset of 248 product categories, each containing 20 samples, structured into 8 subsets. Each model performs zero-shot classification, assigning products to predefined categories without prior exposure. Our findings reveal significant variations in classification accuracy across models, with certain LLMs demonstrating superior scalability and adaptability for real-world e-commerce applications. Based on these insights, we developed an API software to integrate the top-performing models into e-commerce systems, enhancing automation and efficiency. This study underscores the transformative role of LLMs in revolutionizing e-commerce workflows and recommends their adoption for scalable, intelligent product classification.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“LLMs such as GPT-4 [79] and PaLM [80] are trained on massive datasets of text from books, web content, and dialogue corpora. These models exhibit emergent capabilities in natural language understanding, question answering, summarization, dialogue coherence, and even symbolic reasoning [81-83].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [83]
Citations
Cites
Espejel, J. L., Ettifouri, E. H., Alassan, M. S. Y., Chouham, E. M., & Dahhane, W. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100032 · Cited by 148
LLMs in e-commerce: A comparative analysis of GPT and LLaMA models in product review evaluation
Roumeliotis, K. I., Tselikas, N. D., & Nasiopoulos, D. Κ. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2024.100056 · Cited by 127
Self-citationFang, C., Li, X., Fan, Z., Xu, J., Nag, K., Körpeoğlu, E., Kumar, S., & Achan, K. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3661357 · Cited by 75
Applying Machine Learning to Text Segmentation for Information Retrieval
Huang, X., Peng, F., Schuurmans, D., Cercone, N. J., & Robertson, S. E. (2003) · Information Retrieval · doi:10.1023/a:1026028229881 · Cited by 73
The impact of using biased performance metrics on software defect prediction research
Yao, J., & Shepperd, M. (2021) · Information and Software Technology · doi:10.1016/j.infsof.2021.106664 · Cited by 70
LLMs-based machine translation for E-commerce
Gao, D., Chen, K., Chen, B., Dai, H.-F., Jin, L., Jiang, W., Ning, W., Yu, S., Xuan, Q., Cai, X., et al. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125087 · Cited by 44
Haque, M. A., Nahin, K. H., Nirob, J. H., Ahmed, M. K., Singh, N. S. S., Paul, L. C., Algarni, A. D., ELAffendi, M. A., & Ateya, A. A. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.103106 · Cited by 44
Chen, J., Ma, L., Li, X., Thakurdesai, N., Xu, J., Cho, J. H. D., Nag, K., Körpeoğlu, E., Kumar, S., & Achan, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.09858 · Cited by 43
Liu, Y., Zhang, W., Chen, Y., Zhang, Y., Bai, H., Feng, F., Cui, H., Li, Y., & Che, W. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.643 · Cited by 41
Flagged first, then by citations
1 of the 37 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- Wang, 2024, Leveraging large language models for context-aware product discovery in E-commerce search systems, J. Knowl. Learn. Sci. Technol., 3, 300
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
“These models exhibit emergent capabilities in natural language understanding, question answering, summarization, dialogue coherence, and even symbolic reasoning [81–83].”
Self-citationAI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Self-citationXiong, S., Chen, S., He, J., Liu, Y., Mao, J., & Liu, C. (2025) · World Patent Information · doi:10.1016/j.wpi.2025.102380 · Cited by 6
An Explainable AI Multi-Agent Recommender System for Financial Document Access Control
Toudas, K. S., Roumeliotis, K. I., Nasiopoulos, D. Κ., & Georgakopoulos, G. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10742-2 · Cited by 6
Self-citationExploring the architectures of large language models and impact across multiple domains: a review
Waqas, M., Rajab, R., Laghari, A. A., Kryvinska, N., Hejaili, A. A., Khan, N., Khuhro, M. A., & Zhang, F. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11609-3 · Cited by 2
Metadata
- Authors
- Roumeliotis, K. I., Tselikas, N. D., & Nasiopoulos, D. K.
- Affiliations
- University of Peloponnese (GR)
- Corresponding author
- Roumeliotis, Konstantinos I.
- Venue
- Natural Language Processing Journal
- Publisher
- Elsevier BV
- Published
- 2025-06
- Volume
- 11
- Pages
- 100142
- ISSN
- 2949-7191 (ISSN-L)
- OpenAlex
- W4408935345
- Cited by
- 14
- References
- 37
- Citations by year
- 2026: 8 · 2025: 6
- FWCI
- 5.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Natural Language Processing Journal (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- product classification, e-commerce, large language models, zero-shot classification, GPT-4o, Claude 3.5 Sonnet, model comparison
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
