{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:38:01Z","timestamp":1775230681421,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031790287","type":"print"},{"value":"9783031790294","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-79029-4_29","type":"book-chapter","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:25:59Z","timestamp":1738189559000},"page":"414-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ERASMO: Leveraging Large Language Models for\u00a0Enhanced Clustering Segmentation"],"prefix":"10.1007","author":[{"given":"Fillipe","family":"dos Santos Silva","sequence":"first","affiliation":[]},{"given":"Gabriel Kenzo","family":"Kakimoto","sequence":"additional","affiliation":[]},{"given":"Julio Cesar","family":"dos Reis","sequence":"additional","affiliation":[]},{"given":"Marcelo S.","family":"Reis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"29_CR1","unstructured":"Almazrouei, E., et\u00a0al.: Falcon-40b: an open large language model with state-of-the-art performance (2023)"},{"key":"29_CR2","unstructured":"Borisov, V., Se\u00dfler, K., Leemann, T., Pawelczyk, M., Kasneci, G.: Language models are realistic tabular data generators. arXiv preprint arXiv:2210.06280 (2022)"},{"key":"29_CR3","unstructured":"Brooks, N.: Women\u2019s e-commerce clothing reviews (2017). https:\/\/www.kaggle.com\/datasets\/nicapotato\/womens-ecommerce-clothing-reviews"},{"key":"29_CR4","unstructured":"Dataset, Y.: Yelp dataset (2014). http:\/\/www.yelp.com\/dataset_challenge"},{"key":"29_CR5","unstructured":"Kaggle, PetFinder.my: Petfinder.my adoption prediction (2019). https:\/\/www.kaggle.com\/c\/petfinder-adoption-prediction\/data\/"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Keraghel, I., et\u00a0al.: Beyond words: a comparative analysis of llm embeddings for effective clustering. In: Int. Symposium on Intelligent Data Analysis, pp. 205\u2013216. Springer, Heidelberg (2024)","DOI":"10.1007\/978-3-031-58547-0_17"},{"key":"29_CR7","unstructured":"Lewis, P., Perez, A., Petroni, W.t., Rockt\u00e4schel, T., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. In: NIPS (2020)"},{"key":"29_CR8","unstructured":"Liu, Y., He, X., Zhong, T., et\u00a0al.: understanding llms: a comprehensive overview from training to inference. arXiv preprint arXiv:2401.02038 (2024)"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Min, B., Ross, D., others.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 1\u201340 (2023)","DOI":"10.1145\/3605943"},{"key":"29_CR10","doi-asserted-by":"publisher","unstructured":"Moro, S.\u00a0Rita, P., Cortez, P.: Bank marketing. UCI Machine Learning Repository (2012). https:\/\/doi.org\/10.24432\/C5K306","DOI":"10.24432\/C5K306"},{"key":"29_CR11","unstructured":"Olist: Brazilian e-commerce public dataset by olist (2023). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/195341. acessado em: 03 de outubro de 2023"},{"key":"29_CR12","first-page":"36","volume":"2023","author":"O Ourabah","year":"2023","unstructured":"Ourabah, O., et al.: Large scale data using k-means. Mesopotamian J. Big Data 2023, 36\u201345 (2023)","journal-title":"Mesopotamian J. Big Data"},{"key":"29_CR13","unstructured":"Pedregosa, F., Varoquaux, M., Prettenhofer, V., et\u00a0al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)"},{"key":"29_CR14","unstructured":"Petukhova, A., Matos-Carvalho, J.P., Fachada, N.: Text clustering with llm embeddings. arXiv preprint arXiv:2403.15112 (2024)"},{"issue":"6","key":"29_CR15","doi-asserted-by":"publisher","first-page":"3529","DOI":"10.3390\/app13063529","volume":"13","author":"S Pitafi","year":"2023","unstructured":"Pitafi, S., Anwar, T., Sharif, Z.: A taxonomy of machine learning clustering algorithms, challenges, and future realms. Appl. Sci. 13(6), 3529 (2023)","journal-title":"Appl. Sci."},{"issue":"8","key":"29_CR16","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"29_CR17","first-page":"16857","volume":"33","author":"K Song","year":"2020","unstructured":"Song, K., et al.: Mpnet: masked and permuted pre-training for language understanding. Adv. Neural Inf. Process. Syst. 33, 16857\u201316867 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"29_CR18","unstructured":"Tipirneni, S., Adkathimar, N., Hiranandani, V.N., Yuan, C., Reddy, C.K.: Context-aware clustering using large language models. arXiv (2024)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Tissera, M., Asanka, P., et al.: Enhancing customer segmentation using llms and deterministic, independent-of-corpus embeddings. In: 2024 4th (ICARC) (2024)","DOI":"10.1109\/ICARC61713.2024.10499784"},{"key":"29_CR20","unstructured":"Touvron, H., Martin, L., Stone, K., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Viswanathan, V., Gashteovski, K., Lawrence, C., Wu, T., Neubig, G.: Large language models enable few-shot clustering. arXiv preprint arXiv:2307.00524 (2023)","DOI":"10.1162\/tacl_a_00648"},{"key":"29_CR22","unstructured":"Warner, J., Sexauer, J., et\u00a0al.: JDWarner\/scikit-fuzzy: Scikit-Fuzzy version 0.4.2. Zenodo (2019). https:\/\/doi.org\/10.5281\/zenodo.3541386"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Z., Shang, J.: Clusterllm: large language models as a guide for text clustering. arXiv preprint arXiv:2305.14871 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.858"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, P., Lang, Q., Liu, X.: Word embedding of dimensionality reduction for document clustering. In: 2023 35th Chinese Control and Decision Conference (CCDC), pp. 4371\u20134376. IEEE (2023)","DOI":"10.1109\/CCDC58219.2023.10327354"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-79029-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:26:06Z","timestamp":1738189566000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-79029-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031790287","9783031790294"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-79029-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"30 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bel\u00e9m do Par\u00e1","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}