{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T09:42:52Z","timestamp":1759570972603,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032054609","type":"print"},{"value":"9783032054616","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\/978-3-032-05461-6_28","type":"book-chapter","created":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T09:08:15Z","timestamp":1759568895000},"page":"427-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Tuning Transformer-Based LLMs in\u00a0Hierarchical Text Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2656-4375","authenticated-orcid":false,"given":"Joana","family":"Santos","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0556-0707","authenticated-orcid":false,"given":"Nuno","family":"Silva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9933-8287","authenticated-orcid":false,"given":"Carlos","family":"Ferreira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3357-1195","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Gama","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,5]]},"reference":[{"key":"28_CR1","unstructured":"AI@Meta: Llama 3 model card (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Bender, E.M., Koller, A.: Climbing towards NLU: on meaning, form, and understanding in the age of data. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5185\u20135198. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.463","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"28_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR4","unstructured":"Bucher, M.J.J., Martini, M.: Fine-tuned \u2018small\u2019 LLMs (still) significantly outperform zero-shot generative AI models in text classification. arXiv preprint arXiv:2406.08660 (2024)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Androutsopoulos, I.: Large-scale multi-label text classification on EU legislation. arXiv preprint arXiv:1906.02192 (2019)","DOI":"10.18653\/v1\/P19-1636"},{"key":"28_CR6","doi-asserted-by":"publisher","unstructured":"Chy, A.N., Seddiqui, M.H., Das, S.: Bangla news classification using Naive Bayes classifier. In: 16th International Conference Computer and Information Technology, pp. 366\u2013371 (2014). https:\/\/doi.org\/10.1109\/ICCITechn.2014.6997369","DOI":"10.1109\/ICCITechn.2014.6997369"},{"key":"28_CR7","doi-asserted-by":"publisher","unstructured":"Daud, S., Ullah, M., Rehman, A., Saba, T., Dama\u0161evi\u010dius, R., Sattar, A.: Topic classification of online news articles using optimized machine learning models. Computers 12(1) (2023). https:\/\/doi.org\/10.3390\/computers12010016","DOI":"10.3390\/computers12010016"},{"issue":"1","key":"28_CR8","first-page":"2469","volume":"9","author":"N Deb","year":"2020","unstructured":"Deb, N., Jha, V., Panjiyar, A.K., Gupta, R.K.: A comparative analysis of news categorization using machine learning approaches. Int. J. Sci. Technol. Res. 9(1), 2469\u20132472 (2020)","journal-title":"Int. J. Sci. Technol. Res."},{"key":"28_CR9","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018)"},{"key":"28_CR10","doi-asserted-by":"publisher","first-page":"6518","DOI":"10.1109\/ACCESS.2024.3349952","volume":"12","author":"J Fields","year":"2024","unstructured":"Fields, J., Chovanec, K., Madiraju, P.: A survey of text classification with transformers: how wide? how large? how long? how accurate? how expensive? how safe? IEEE Access 12, 6518\u20136531 (2024)","journal-title":"IEEE Access"},{"key":"28_CR11","unstructured":"Guardian, T.: Latest news, sport and opinion from the guardian. https:\/\/www.theguardian.com\/europe"},{"key":"28_CR12","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention. In: International Conference on Learning Representations (2021)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Jain, V., et al.: Higen: hierarchy-aware sequence generation for hierarchical text classification. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol.\u00a02024, p.\u00a01354 (2024)","DOI":"10.18653\/v1\/2024.eacl-long.82"},{"key":"28_CR14","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023)"},{"key":"28_CR15","doi-asserted-by":"publisher","unstructured":"Kareem, I., Awan, S.M.: Pakistani media fake news classification using machine learning classifiers (2019). https:\/\/doi.org\/10.1109\/ICIC48496.2019.8966734","DOI":"10.1109\/ICIC48496.2019.8966734"},{"key":"28_CR16","doi-asserted-by":"publisher","unstructured":"Katari, R., Myneni, M.B.: A survey on news classification techniques. In: 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA), pp.\u00a01\u20135 (2020). https:\/\/doi.org\/10.1109\/ICCSEA49143.2020.9132866","DOI":"10.1109\/ICCSEA49143.2020.9132866"},{"key":"28_CR17","unstructured":"Kostina, A., Dikaiakos, M.D., Stefanidis, D., Pallis, G.: Large language models for text classification: case study and comprehensive review (2025)"},{"key":"28_CR18","unstructured":"Lee, Y., et\u00a0al.: Characterizing and efficiently accelerating multimodal generation model inference. arXiv preprint arXiv:2410.00215 (2024)"},{"issue":"2","key":"28_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100017","volume":"1","author":"Y Liu","year":"2023","unstructured":"Liu, Y., et al.: Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiol. 1(2), 100017 (2023)","journal-title":"Meta-Radiol."},{"key":"28_CR20","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019)"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Plaud, R., Labeau, M., Saillenfest, A., Bonald, T.: Revisiting hierarchical text classification: inference and metrics. arXiv preprint arXiv:2410.01305 (2024)","DOI":"10.18653\/v1\/2024.conll-1.18"},{"key":"28_CR22","unstructured":"Priem, J., Piwowar, H., Orr, R.: Openalex: a fully-open index of scholarly works, authors, venues, institutions, and concepts (2022)"},{"key":"28_CR23","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv abs\/1910.01108 (2019)"},{"key":"28_CR24","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning, vol. 2017-December, pp. 4078\u20134088 (2017)"},{"key":"28_CR25","unstructured":"Sun, A., Lim, E.P.: Hierarchical text classification and evaluation. In: Proceedings 2001 IEEE International Conference on Data Mining, pp. 521\u2013528. IEEE (2001)"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"du\u00a0Toit, J., Dunaiski, M.: Prompt tuning discriminative language models for hierarchical text classification. Nat. Lang. Process. 1\u201318 (2024)","DOI":"10.1017\/nlp.2024.51"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Torba, F., Gravier, C., Laclau, C., Kammoun, A., Subercaze, J.: A study on hierarchical text classification as a seq2seq task. In: European Conference on Information Retrieval, pp. 287\u2013296. Springer (2024)","DOI":"10.1007\/978-3-031-56063-7_20"},{"key":"28_CR28","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"28_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"28_CR30","unstructured":"Veeranna, S.P., Nam, J., Menc\u00eda, E.L., F\u00fcrnkranz, J.: Using semantic similarity for multi-label zero-shot classification of text documents, pp. 423\u2013428 (2016)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Wilkho, R.S., Chang, S., Gharaibeh, N.G.: FF-BERT: a BERT-based ensemble for automated classification of web-based text on flash flood events. Adv. Eng. Inform. 59, 102293 (2024)","DOI":"10.1016\/j.aei.2023.102293"},{"key":"28_CR32","unstructured":"Yogatama, D., Dyer, C., Ling, W., Blunsom, P.: Generative and discriminative text classification with recurrent neural networks (2017)"},{"key":"28_CR33","unstructured":"Zheng, C., Wu, G., Bao, F., Cao, Y., Li, C., Zhu, J.: Revisiting discriminative vs. generative classifiers: theory and implications. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 42420\u201342477. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Discovery Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05461-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T09:08:25Z","timestamp":1759568905000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05461-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783032054609","9783032054616"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05461-6_28","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":"5 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Discovery Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ds2025.ijs.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}