{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T12:29:00Z","timestamp":1769776140389,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032159892","type":"print"},{"value":"9783032159908","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-15990-8_21","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:00:07Z","timestamp":1769716807000},"page":"306-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Model Merging Configurations for\u00a0Brazilian Portuguese Sentiment and\u00a0Hate Speech Classification with\u00a0TIES-Merging and\u00a0SaDE"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7173-1132","authenticated-orcid":false,"given":"Viviane","family":"Galv\u00e3o","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2012-7802","authenticated-orcid":false,"given":"Heder","family":"Bernardino","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"issue":"2","key":"21_CR1","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s42256-024-00975-8","volume":"7","author":"T Akiba","year":"2025","unstructured":"Akiba, T., Shing, M., Tang, Y., Sun, Q., Ha, D.: Evolutionary optimization of model merging recipes. Nat. Mach. Intell. 7(2), 195\u2013204 (2025)","journal-title":"Nat. Mach. Intell."},{"key":"21_CR2","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"21_CR3","unstructured":"Carmo, D., Piau, M., Campiotti, I., Nogueira, R., Lotufo, R.: Ptt5: pretraining and validating the t5 model on Brazilian Portuguese data. arXiv preprint arXiv:2008.09144 (2020)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Costa, P.B., Pavan, M.C., Santos, W.R., Silva, S.C., Paraboni, I.: Bertabaporu: assessing a genre-specific language model for Portuguese nlp. In: Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pp. 217\u2013223 (2023) (2023)","DOI":"10.26615\/978-954-452-092-2_024"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Das, S., Suganthan, P.N.: Differential evolution: a survey of the state-of-the-art. Trans. Evol. Comp 15(1) (2011)","DOI":"10.1109\/TEVC.2010.2059031"},{"key":"21_CR6","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized llms. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 10088\u201310115. Curran Associates, Inc. (2023)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: In: Pre-training of Deep Bidirectional Transformers for Language Understanding, pp. 4171\u20134186. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Goddard, C., et\u00a0al.: Arcee\u2019s MergeKit: a toolkit for merging large language models, pp. 477\u2013485. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"21_CR9","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models (2022)"},{"key":"21_CR10","unstructured":"Ilharco, G., et\u00a0al.: Editing models with task arithmetic (2023)"},{"key":"21_CR11","unstructured":"Larcher, C., Piau, M., Finardi, P., Gengo, P., Esposito, P., Carid\u00e1, V.: Cabrita: closing the gap for foreign languages (2023)"},{"key":"21_CR12","unstructured":"Liu, Y., et\u00a0al.: Roberta: a robustly optimized bert pretraining approach (2019)"},{"issue":"2","key":"21_CR13","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TNNLS.2021.3100554","volume":"34","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Sun, Y., Xue, B., Zhang, M., Yen, G.G., Tan, K.C.: A survey on evolutionary neural architecture search. IEEE Trans. Neural Netw. Learn. Syst. 34(2), 550\u2013570 (2023)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Lozano, J.A., Larra\u00f1aga, P., Inza, I.n., Bengoetxea, E.: Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms (Studies in Fuzziness and Soft Computing). Springer-Verlag, Cham (2006)","DOI":"10.1007\/3-540-32494-1"},{"key":"21_CR15","unstructured":"Mencattini, T., Minut, A.R., Crisostomi, D., Santilli, A., Rodol\u00e0, E.: Merge$$^3$$: efficient evolutionary merging on consumer-grade gpus (2025)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, vol.\u00a02, pp. 1045\u20131048. Makuhari (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Pires, R., Abonizio, H., Almeida, T.S., Nogueira, R.: Sabi\u00e1: Portuguese Large Language Models, pp. 226\u2013240. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-45392-2_15"},{"issue":"2","key":"21_CR18","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/TEVC.2008.927706","volume":"13","author":"AK Qin","year":"2008","unstructured":"Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. Evol. Comput. 13(2), 398\u2013417 (2008)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"21_CR19","volume-title":"Improving language understanding by generative pre-training","author":"A Radford","year":"2018","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training. Technical report, OpenAI (2018)"},{"key":"21_CR20","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et\u00a0al.: Language models are unsupervised multitask learners. Technical Report 8, OpenAI (2019)"},{"issue":"140","key":"21_CR21","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC \u201920. IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"21_CR24","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter (2020)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Shoemake, K.: Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques, pp. 245\u2013254 (1985)","DOI":"10.1145\/325334.325242"},{"key":"21_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-61377-8_28","volume-title":"Intelligent Systems","author":"F Souza","year":"2020","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: Pretrained BERT Models for Brazilian Portuguese. In: Cerri, R., Prati, R.C. (eds.) BRACIS 2020. LNCS (LNAI), vol. 12319, pp. 403\u2013417. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61377-8_28"},{"key":"21_CR27","unstructured":"Storn, R., Price, K.: Differential evolution - a simple and efficient adaptive scheme for global optimization over continuous spaces, vol.\u00a03. ICSI Berkeley (1995)"},{"key":"21_CR28","unstructured":"Utans, J.: Weight averaging for neural networks and local resampling schemes. In: Proceedings of AAAI-96 Workshop on Integrating Multiple Learned Models, pp. 133\u2013138. AAAI Press, Citeseer (1996)"},{"key":"21_CR29","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"21_CR30","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Guyon, I., et\u00a0al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Warner, B., et\u00a0al.: Smarter, better, faster, longer: a modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference (2025)","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"21_CR32","unstructured":"White, T.: Sampling generative networks (2016)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Wilcoxon, F.: Individual Comparisons by Ranking Methods, pp. 196\u2013202. Springer, New York (1992)","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"21_CR34","unstructured":"Wortsman, M., et\u00a0al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 23965\u201323998. PMLR (2022)"},{"key":"21_CR35","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C., Bansal, M.: In: Ties-merging: resolving interference when merging models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923. Curran Associates Inc., Red Hook (2023)"},{"key":"21_CR36","unstructured":"Yang, E., et\u00a0al.: Model merging in llms, mllms, and beyond: methods, theories, applications and opportunities (2024)"},{"key":"21_CR37","unstructured":"Yu, L., Yu, B., Yu, H., Huang, F., Li, Y.: Language models are super mario: absorbing abilities from homologous models as a free lunch. In: Proceedings of the 41st International Conference on Machine Learning. ICML\u201924. JMLR.org (2024)"},{"key":"21_CR38","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models (2025)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-15990-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:00:11Z","timestamp":1769716811000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-15990-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032159892","9783032159908"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-15990-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","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":"Fortaleza-CE","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bracis.sbc.org.br\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}