{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:19:19Z","timestamp":1778167159576,"version":"3.51.4"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012818","name":"Comunidad de Madrid","doi-asserted-by":"publisher","award":["TEC-2024\/COM-404"],"award-info":[{"award-number":["TEC-2024\/COM-404"]}],"id":[{"id":"10.13039\/100012818","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00267476"],"award-info":[{"award-number":["RS-2023-00267476"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CHISTERA IV Cofund 2021 program","award":["PCI2022-134990-2"],"award-info":[{"award-number":["PCI2022-134990-2"]}]},{"DOI":"10.13039\/501100000780","name":"European Comission","doi-asserted-by":"crossref","award":["DIGITAL-2023-DEPLOY- 04-EDMO-HUBS 101158511"],"award-info":[{"award-number":["DIGITAL-2023-DEPLOY- 04-EDMO-HUBS 101158511"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Calouste Gulbenkian Foundation"},{"DOI":"10.13039\/501100003759","name":"Universidad Polit\u00e9cnica de Madrid","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003759","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>As social media and digital platforms become more influential, the spread of hate speech has accelerated, inflicting serious harm on individuals, communities, and society as a whole. Addressing this challenge is further complicated by the limitations of traditional text data augmentation techniques\u2014such as adding noise to the original text, substituting words based on context, or rephrasing sentences\u2014which often fail to introduce new perspectives that could help classifiers generalize better to new instances. This limitation is especially critical in fields like hate speech detection, where creating datasets is highly labor-intensive, involving the collection of positive samples and expert labeling. In this work, we present an automatic text data augmentation method based on large language models (LLMs) using demonstration-based generation. Our approach generates diverse samples that maintain the original writing style, effectively bridging semantic gaps in the data. While our method focuses on low-resource hate speech datasets, we have empirically demonstrated its potential and consistency even in larger and more robust dataset scenarios. The careful design of the prompt, combined with token sampling strategies, positions our method as the most consistent alternative for LLM-based synthetic data generation compared to existing state-of-the-art methods and prompts. Our benchmarking includes (1) <jats:italic>CMSB<\/jats:italic>, a dataset centered on sexism; (2) <jats:italic>ETHOS<\/jats:italic>, a diverse dataset encompassing multiple forms of hate speech; (3) <jats:italic>Stormfront<\/jats:italic>, which contains white supremacist discourse; and (4) <jats:italic>Antiasian<\/jats:italic>, an anti-Asian hate speech dataset. We outperform other traditional augmentation methods such as <jats:italic>NLPAug<\/jats:italic> or <jats:italic>BackTranslation<\/jats:italic> and benchmark with promising results against another LLM-based techniques. We consistently achieve an F1-score improvement of approximately 4\u20136% in low-resource scenarios and 1\u20132% on full datasets. These gains are notably higher compared to both the absence of augmentation and alternative augmentation methods.<\/jats:p>","DOI":"10.1007\/s00607-025-01518-8","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:44:33Z","timestamp":1751521473000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["LLM synthetic generation to enhance online content moderation generalization in hate speech scenarios"],"prefix":"10.1007","volume":"107","author":[{"given":"Adri\u00e1n","family":"Gir\u00f3n","sequence":"first","affiliation":[]},{"given":"Javier","family":"Huertas-Tato","sequence":"additional","affiliation":[]},{"given":"David","family":"Camacho","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"1518_CR1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.21018\/rjcpr.2021.1.322","volume":"23","author":"O \u015etef\u0103ni\u0163\u0103","year":"2021","unstructured":"\u015etef\u0103ni\u0163\u0103 O, Buf D-M (2021) Hate speech in social media and its effects on the LGBT community: a review of the current research. Roman J Commun Public Relat 23:47\u201355. https:\/\/doi.org\/10.21018\/rjcpr.2021.1.322","journal-title":"Roman J Commun Public Relat"},{"issue":"Autumn","key":"1518_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3427478.3427482","volume":"2020","author":"M Das","year":"2020","unstructured":"Das M, Mathew B, Saha P, Goyal P, Mukherjee A (2020) Hate speech in online social media. ACM SIGWEB Newsl 2020(Autumn):1\u20138. https:\/\/doi.org\/10.1145\/3427478.3427482","journal-title":"ACM SIGWEB Newsl"},{"issue":"24","key":"1518_CR3","doi-asserted-by":"publisher","first-page":"12003","DOI":"10.3390\/app112412003","volume":"11","author":"M Lopez-Sanchez","year":"2021","unstructured":"Lopez-Sanchez M, M\u00fcller A (2021) On simulating the propagation and countermeasures of hate speech in social networks. Appl Sci 11(24):12003. https:\/\/doi.org\/10.3390\/app112412003","journal-title":"Appl Sci"},{"key":"1518_CR4","doi-asserted-by":"publisher","unstructured":"Mathew B, Dutt R, Goyal P, Mukherjee A (2019) Spread of hate speech in online social media. In: Proceedings of the 10th ACM conference on web science, pp 173\u2013182. https:\/\/doi.org\/10.1145\/3292522.3326034","DOI":"10.1145\/3292522.3326034"},{"key":"1518_CR5","doi-asserted-by":"publisher","unstructured":"Ilan T, Vilenchik D (2022) HARALD: Augmenting hate speech data sets with real data. In: Goldberg Y, Kozareva Z, Zhang Y (eds) Findings of the association for computational linguistics: EMNLP 2022. Association for Computational Linguistics, Abu Dhabi, pp 2241\u20132248. https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.165","DOI":"10.18653\/v1\/2022.findings-emnlp.165"},{"issue":"1","key":"1518_CR6","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1080\/13600834.2018.1494417","volume":"28","author":"N Alkiviadou","year":"2019","unstructured":"Alkiviadou N (2019) Hate speech on social media networks: towards a regulatory framework? Inf Commun Technol Law 28(1):19\u201335. https:\/\/doi.org\/10.1080\/13600834.2018.1494417","journal-title":"Inf Commun Technol Law"},{"key":"1518_CR7","unstructured":"Murtfeldt R, Alterman N, Kahveci I, West JD (2024) RIP Twitter API: a eulogy to its vast research contributions. arXiv"},{"key":"1518_CR8","doi-asserted-by":"crossref","unstructured":"Feng SY, Gangal V, Wei J, Chandar S, Vosoughi S, Mitamura T, Hovy E (2021) A survey of data augmentation approaches for NLP. arXiv","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"1518_CR9","unstructured":"Mohamadi S, Mujtaba G, Le N, Doretto G, Adjeroh DA (2023) ChatGPT in the age of generative ai and large language models: a concise survey. arXiv:2307.04251v2"},{"key":"1518_CR10","unstructured":"Jiang AQ, Sablayrolles A, Mensch A, Bamford C, Chaplot DS, Casas D, Bressand F, Lengyel G, Lample G, Saulnier L, Lavaud LR, Lachaux M-A, Stock P, Scao TL, Lavril T, Wang T, Lacroix T, Sayed WE (2023) Mistral 7B. arXiv. doi:1048550\/arXiv.2310.06825"},{"key":"1518_CR11","unstructured":"Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv. doi:1048550\/arXiv.1712.04621"},{"key":"1518_CR12","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le Q (2020) RandAugment: practical automated data augmentation with a reduced search space. In: Advances in neural information processing systems, vol 33. Curran Associates, Inc., pp 18613\u201318624","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"1518_CR13","doi-asserted-by":"publisher","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models arXiv. https:\/\/doi.org\/10.48550\/arXiv.2006.11239","DOI":"10.48550\/arXiv.2006.11239"},{"key":"1518_CR14","doi-asserted-by":"publisher","unstructured":"Praveen\u00a0Gujjar J, Prasanna\u00a0Kumar HR, Guru\u00a0Prasad MS (2023) Advanced NLP framework for text processing. In: 2023 6th international conference on information systems and computer networks (ISCON), pp 1\u20133. https:\/\/doi.org\/10.1109\/ISCON57294.2023.10112058","DOI":"10.1109\/ISCON57294.2023.10112058"},{"key":"1518_CR15","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2016) Improving neural machine translation models with monolingual data. In: Erk K, Smith NA (eds) Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Berlin, pp 86\u201396. https:\/\/doi.org\/10.18653\/v1\/P16-1009","DOI":"10.18653\/v1\/P16-1009"},{"key":"1518_CR16","doi-asserted-by":"publisher","unstructured":"Wei J, Zou K (2019) EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: Inui K, Jiang J, Ng V, Wan X (eds) Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, pp 6382\u20136388. https:\/\/doi.org\/10.18653\/v1\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"1518_CR17","doi-asserted-by":"publisher","unstructured":"Belinkov Y, Bisk Y (2018) Synthetic and natural noise both break neural machine translation. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1711.02173","DOI":"10.48550\/arXiv.1711.02173"},{"key":"1518_CR18","doi-asserted-by":"publisher","unstructured":"Yang H, Li K (2023) Boosting text augmentation via hybrid instance filtering framework. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the association for computational linguistics: ACL 2023. Association for Computational Linguistics, Toronto, pp 1652\u20131669. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.105","DOI":"10.18653\/v1\/2023.findings-acl.105"},{"key":"1518_CR19","doi-asserted-by":"publisher","unstructured":"Pavlick E, Rastogi P, Ganitkevitch J, Van\u00a0Durme B, Callison-Burch C (2015) PPDB 2.0: better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification. In: Zong C, Strube M (eds) Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 2: short papers). Association for Computational Linguistics, Beijing, pp 425\u2013430. https:\/\/doi.org\/10.3115\/v1\/P15-2070","DOI":"10.3115\/v1\/P15-2070"},{"issue":"3","key":"1518_CR20","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.32604\/cmc.2023.040202","volume":"76","author":"F Mohammad","year":"2023","unstructured":"Mohammad F, Khan M, Nawaz Khan Marwat S, Jan N, Gohar N, Bilal M, Al-Rasheed A (2023) Text augmentation-based model for emotion recognition using transformers. Comput Mater Contin 76(3):3523\u20133547. https:\/\/doi.org\/10.32604\/cmc.2023.040202","journal-title":"Comput Mater Contin"},{"key":"1518_CR21","unstructured":"Tarj\u2019an B, Szasz\u2019ak G, Fegy\u2019o T, Mihajlik P (2020) Deep transformer based data augmentation with subword units for morphologically rich online ASR. ArXiv"},{"key":"1518_CR22","doi-asserted-by":"publisher","unstructured":"Longpre S, Wang Y, DuBois C (2020) How effective is task-agnostic data augmentation for pretrained transformers? In: Findings of the association for computational linguistics: EMNLP 2020. Association for Computational Linguistics, pp 4401\u20134411. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.394","DOI":"10.18653\/v1\/2020.findings-emnlp.394"},{"key":"1518_CR23","unstructured":"Schmidt RM (2019) Recurrent neural networks (RNNs): a gentle introduction and overview. arXiv. doi:1048550\/arXiv.1912.05911"},{"key":"1518_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735\u201380. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"1518_CR25","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2023). Attention is all you need. https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"1518_CR26","doi-asserted-by":"publisher","unstructured":"Kobayashi S (2018) Contextual augmentation: data augmentation by words with paradigmatic relations. In: Walker M, Ji H, Stent A (eds) Proceedings of the 2018 conference of the North American Chapter of the Association for Computational Linguistics: human language technologies, volume 2 (short papers). Association for Computational Linguistics, New Orleans, pp 452\u2013457. https:\/\/doi.org\/10.18653\/v1\/N18-2072","DOI":"10.18653\/v1\/N18-2072"},{"key":"1518_CR27","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","DOI":"10.48550\/arXiv.1810.04805"},{"key":"1518_CR28","doi-asserted-by":"crossref","unstructured":"Kumar V, Choudhary A, Cho E (2021) Data augmentation using pre-trained transformer models. arXiv","DOI":"10.18653\/v1\/2020.lifelongnlp-1.3"},{"key":"1518_CR29","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv. doi:1048550\/arXiv.1412.3555"},{"key":"1518_CR30","unstructured":"Dai H, Liu Z, Liao W, Huang X, Cao Y, Wu Z, Zhao L, Xu S, Liu W, Liu N, Li S, Zhu D, Cai H, Sun L, Li Q, Shen D, Liu T, Li X (2023) AugGPT: leveraging ChatGPT for text data augmentation. arXiv"},{"key":"1518_CR31","doi-asserted-by":"crossref","unstructured":"Yoo KM, Park D, Kang J, Lee S-W, Park W (2021) GPT3Mix: leveraging large-scale language models for text augmentation. arXiv","DOI":"10.18653\/v1\/2021.findings-emnlp.192"},{"key":"1518_CR32","doi-asserted-by":"crossref","unstructured":"Li Z, Zhu H, Lu Z, Yin M (2023) Synthetic data generation with large language models for text classification: potential and limitations. arXiv","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"1518_CR33","doi-asserted-by":"crossref","unstructured":"Ye J, Gao J, Li Q, Xu H, Feng J, Wu Z, Yu T, Kong L (2022) ZeroGen: efficient zero-shot learning via dataset generation. arXiv","DOI":"10.18653\/v1\/2022.emnlp-main.801"},{"key":"1518_CR34","doi-asserted-by":"publisher","unstructured":"Wu T, Ribeiro MT, Heer J, Weld D (2021) Polyjuice: generating counterfactuals for explaining, evaluating, and improving models. In: Zong C, Xia F, Li W, Navigli R (eds) Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers). Association for Computational Linguistics, pp 6707\u20136723. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.523","DOI":"10.18653\/v1\/2021.acl-long.523"},{"key":"1518_CR35","doi-asserted-by":"crossref","unstructured":"Dixit T, Paranjape B, Hajishirzi H, Zettlemoyer L (2022) CORE: a retrieve-then-edit framework for counterfactual data generation. arXiv","DOI":"10.18653\/v1\/2022.findings-emnlp.216"},{"key":"1518_CR36","doi-asserted-by":"crossref","unstructured":"Chen Z, Gao Q, Bosselut A, Sabharwal A, Richardson K (2023) DISCO: distilling counterfactuals with large language models. arXiv","DOI":"10.18653\/v1\/2023.acl-long.302"},{"key":"1518_CR37","unstructured":"Kruschwitz U, Schmidhuber M (2024) Llm-based synthetic datasets: applications and limitations in toxicity detection. In: Kumar R, Ojha AK, Malmasi S, Chakravarthi BR, Lahiri B, Singh S, Ratan S (eds.) Proceedings of the fourth workshop on threat, aggression & cyberbullying @ LREC-COLING-2024. ELRA and ICCL, Torino, pp 37\u201351. https:\/\/aclanthology.org\/2024.trac-1.6\/"},{"key":"1518_CR38","doi-asserted-by":"publisher","unstructured":"Pendzel S, Wullach T, Adler A, Minkov E (2023) Generative ai for hate speech detection: evaluation and findings (arXiv:2311.09993), https:\/\/doi.org\/10.48550\/arXiv.2311.09993. arXiv:2311.09993","DOI":"10.48550\/arXiv.2311.09993"},{"key":"1518_CR39","unstructured":"Zelikman E, Wu Y, Mu J, Goodman ND (2022) STaR: bootstrapping reasoning with reasoning. arXiv"},{"key":"1518_CR40","unstructured":"Konen K, Jentzsch S, Diallo D, Sch\u00fctt P, Bensch O, Baff RE, Opitz D, Hecking T (2024) Style vectors for steering generative large language model. arXiv"},{"key":"1518_CR41","doi-asserted-by":"publisher","unstructured":"Samory M, Sen I, Kohne J, Fl\u00f6ck F, Wagner C (2021) \u201cCall me sexist, but...\u201d : revisiting sexism detection using psychological scales and adversarial samples. In: Proceedings of the international AAAI conference on web and social media, vol 15. Association for the Advancement of Artificial Intelligence (AAAI), pp 573\u2013584. https:\/\/doi.org\/10.1609\/icwsm.v15i1.18085","DOI":"10.1609\/icwsm.v15i1.18085"},{"issue":"1","key":"1518_CR42","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/3625679","volume":"2","author":"A Khullar","year":"2024","unstructured":"Khullar A, Nkemelu D, Nguyen VC, Best ML (2024) Hate speech detection in limited data contexts using synthetic data generation. ACM J Comput Sustain Soc 2(1):4\u20131418. https:\/\/doi.org\/10.1145\/3625679","journal-title":"ACM J Comput Sustain Soc"},{"key":"1518_CR43","doi-asserted-by":"crossref","unstructured":"Hartvigsen T, Gabriel S, Palangi H, Sap M, Ray D, Kamar E (2022) ToxiGen: a large-scale machine-generated dataset for adversarial and implicit hate speech detection. arXiv","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"1518_CR44","doi-asserted-by":"crossref","unstructured":"Gir\u00f3n A, Collell G, Hassan F, Huertas-Tato J, Camacho D (2025) Low-resource dataset synthetic generation for hate speech detection. In: Barhamgi M, Wang H, Wang X, A\u00efmeur E, Mrissa M, Chikhaoui B, Boukadi K, Grati R, Maamar Z (eds) Web information systems engineering\u2014WISE 2024 PhD symposium, demos and workshops. Springer, Singapore, pp 75\u201389","DOI":"10.1007\/978-981-96-1483-7_6"},{"key":"1518_CR45","doi-asserted-by":"publisher","unstructured":"Mollas I, Chrysopoulou Z, Karlos S, Tsoumakas G (2022) ETHOS: an online hate speech detection dataset. Complex Intell Syst 8(6):4663\u20134678. https:\/\/doi.org\/10.1007\/s40747-021-00608-2arXiv:2006.08328 [cs, stat]","DOI":"10.1007\/s40747-021-00608-2"},{"key":"1518_CR46","doi-asserted-by":"publisher","unstructured":"de\u00a0Gibert O, Perez N, Garc\u00eda-Pablos A, Cuadros M (2018) Hate speech dataset from a white supremacy forum. In: Fi\u0161er D, Huang R, Prabhakaran V, Voigt R, Waseem Z, Wernimont J (eds) Proceedings of the 2nd workshop on abusive language online (ALW2). Association for Computational Linguistics, Brussels, pp 11\u201320. https:\/\/doi.org\/10.18653\/v1\/W18-5102","DOI":"10.18653\/v1\/W18-5102"},{"key":"1518_CR47","doi-asserted-by":"crossref","unstructured":"He B, Ziems C, Soni S, Ramakrishnan N, Yang D, Kumar S (2021) racism is a virus: anti-Asian hate and counterspeech in social media during the COVID-19 crisis. arXiv. doi:1048550\/arXiv.2005.12423","DOI":"10.1145\/3487351.3488324"},{"key":"1518_CR48","unstructured":"Ma E (2019) NLP augmentation. https:\/\/github.com\/makcedward\/nlpaug"},{"key":"1518_CR49","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R (2022) Training language models to follow instructions with human feedback. arXiv. doi:1048550\/arXiv.2203.02155"},{"key":"1518_CR50","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) RoBERTa: a robustly optimized bert pretraining approach"},{"key":"1518_CR51","unstructured":"He P, Liu X, Gao J, Chen W (2021) DeBERTa: decoding-enhanced BERT with disentangled attention. arXiv"},{"key":"1518_CR52","doi-asserted-by":"crossref","unstructured":"Meister C, Pimentel T, Wiher G, Cotterell R (2023) Locally typical sampling. arXiv","DOI":"10.1162\/tacl_a_00536"},{"key":"1518_CR53","unstructured":"Keskar NS, McCann B, Varshney LR, Xiong C, Socher R (2019) CTRL: a conditional transformer language model for controllable generation. arXiv"},{"key":"1518_CR54","doi-asserted-by":"publisher","unstructured":"Bucher MJJ, Martini M (2024) Fine-tuned \u201csmall\u201d llms (still) significantly outperform zero-shot generative ai models in text classification (arXiv:2406.08660) https:\/\/doi.org\/10.48550\/arXiv.2406.08660. arXiv:2406.08660","DOI":"10.48550\/arXiv.2406.08660"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-025-01518-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-025-01518-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-025-01518-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T11:55:16Z","timestamp":1756468516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-025-01518-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":54,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1518"],"URL":"https:\/\/doi.org\/10.1007\/s00607-025-01518-8","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]},"assertion":[{"value":"24 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"164"}}