{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:14:27Z","timestamp":1773414867532,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031969614","type":"print"},{"value":"9783031969621","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\/978-3-031-96962-1_2","type":"book-chapter","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T07:33:58Z","timestamp":1751009638000},"page":"17-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LLMs and\u00a0Finetuning: Benchmarking Cross-Domain Performance for\u00a0Hate Speech Detection"],"prefix":"10.1007","author":[{"given":"Ahmad","family":"Nasir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aadish","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kokil","family":"Jaidka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saifuddin","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Antypas, D., Camacho-Collados, J.: Robust hate speech detection in social media: a cross-dataset empirical evaluation. In: The 7th Workshop on Online Abuse and Harms (WOAH), pp. 231\u2013242 (July 2023)","DOI":"10.18653\/v1\/2023.woah-1.25"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Arango, A., P\u00e9rez, J., Poblete, B.: Hate speech detection is not as easy as you may think: a closer look at model validation. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 45\u201354 (2019)","DOI":"10.1145\/3331184.3331262"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chandrasekharan, E., Samory, M., Srinivasan, A., Gilbert, E.: The bag of communities: identifying abusive behavior online with preexisting internet data. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 3175\u20133187 (2017)","DOI":"10.1145\/3025453.3026018"},{"key":"2_CR4","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatgpt quality. See https:\/\/vicuna.lmsys.org. Accessed 14 April 2023 (2023)"},{"key":"2_CR5","unstructured":"Conversation, A.: Toxic comment classification challenge: Identify and classify toxic online comments (2017)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the International AAAI Conference on Web and Social Media, vol.\u00a011, pp. 512\u2013515 (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"2_CR7","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLORA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314 (2023)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Diener, E., Diener, M., Diener, C.: Factors predicting the subjective well-being of nations. In: Culture and well-being, pp. 43\u201370. Springer (2009)","DOI":"10.1007\/978-90-481-2352-0_3"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Dmonte, A., Arya, T., Ranasinghe, T., Zampieri, M.: Towards generalized offensive language identification. In: Proceedings of the International Conference on Advances in Social Networks Analysis and Mining (2024)","DOI":"10.1007\/978-3-031-78541-2_17"},{"issue":"3","key":"2_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102524","volume":"58","author":"P Fortuna","year":"2021","unstructured":"Fortuna, P., Soler-Company, J., Wanner, L.: How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets? Inform. Process. Manage. 58(3), 102524 (2021)","journal-title":"Inform. Process. Manage."},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Founta, A., et al.: Large scale crowdsourcing and characterization of twitter abusive behavior. In: Proceedings of the International AAAI Conference on Web and Social Media, vol.\u00a012 (2018)","DOI":"10.1609\/icwsm.v12i1.14991"},{"key":"2_CR12","unstructured":"Gao, L., Huang, R.: Detecting online hate speech using context aware models. arXiv preprint arXiv:1710.07395 (2017)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Gr\u00f6ndahl, T., Pajola, L., Juuti, M., Conti, M., Asokan, N.: All you need is\" love\" evading hate speech detection. In: Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security, pp. 2\u201312 (2018)","DOI":"10.1145\/3270101.3270103"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Herz, M., Moln\u00e1r, P.: The content and context of hate speech: Rethinking regulation and responses. Cambridge University Press (2012)","DOI":"10.1017\/CBO9781139042871"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Karan, M., \u0160najder, J.: Cross-domain detection of abusive language online. In: Proceedings of the 2nd Workshop on Abusive Language Online (ALW2), pp. 132\u2013137 (2018)","DOI":"10.18653\/v1\/W18-5117"},{"key":"2_CR16","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s41701-019-00065-w","volume":"4","author":"V Kolhatkar","year":"2020","unstructured":"Kolhatkar, V., Wu, H., Cavasso, L., Francis, E., Shukla, K., Taboada, M.: The SFU opinion and comments corpus: A corpus for the analysis of online news comments. Corpus Pragmatics 4, 155\u2013190 (2020)","journal-title":"Corpus Pragmatics"},{"key":"2_CR17","unstructured":"Kumar, R., Ojha, A.K., Malmasi, S., Zampieri, M.: Benchmarking aggression identification in social media. In: Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018), pp. 1\u201311 (2018)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Mandl, T., et al.: Overview of the HASOC track at fire 2019: Hate speech and offensive content identification in Indo-European languages. In: Proceedings of the 11th Annual Meeting of the Forum for Information Retrieval Evaluation, pp. 14\u201317 (2019)","DOI":"10.1145\/3368567.3368584"},{"key":"2_CR19","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S.: PEFT: State-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Maronikolakis, A., Wisiorek, A., Nann, L., Jabbar, H., Udupa, S., Sch\u00fctze, H.: Listening to affected communities to define extreme speech: dataset and experiments. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 1089\u20131104 (May 2022)","DOI":"10.18653\/v1\/2022.findings-acl.87"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Mozafari, M., Farahbakhsh, R., Crespi, N.: A BERT-based transfer learning approach for hate speech detection in online social media. In: Complex Networks and Their Applications VIII: Volume 1 Proceedings of the Eighth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2019 8, pp. 928\u2013940. Springer (2020)","DOI":"10.1007\/978-3-030-36687-2_77"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Pamungkas, E.W., Patti, V.: Cross-domain and cross-lingual abusive language detection: A hybrid approach with deep learning and a multilingual lexicon. In: Proceedings of the 57th Annual Meeting Of the Association For Computational Linguistics: Student Research Workshop, pp. 363\u2013370 (2019)","DOI":"10.18653\/v1\/P19-2051"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Qian, J., Bethke, A., Liu, Y., Belding, E., Wang, W.Y.: A benchmark dataset for learning to intervene in online hate speech. arXiv preprint arXiv:1909.04251 (2019)","DOI":"10.18653\/v1\/D19-1482"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Rosenthal, S., Atanasova, P., Karadzhov, G., Zampieri, M., Nakov, P.: Solid: A large-scale semi-supervised dataset for offensive language identification. arXiv preprint arXiv:2004.14454 (2020)","DOI":"10.18653\/v1\/2021.findings-acl.80"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Salminen, J., et al.: Anatomy of online hate: developing a taxonomy and machine learning models for identifying and classifying hate in online news media. In: Proceedings of the International AAAI Conference on Web and Social Media, vol.\u00a012 (2018)","DOI":"10.1609\/icwsm.v12i1.15028"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Salminen, J., Hopf, M., Chowdhury, S.A., Jung, S.g., Almerekhi, H., Jansen, B.J.: Developing an online hate classifier for multiple social media platforms. Human-centric Comput. Inform. Sci. 10, 1\u201334 (2020)","DOI":"10.1186\/s13673-019-0205-6"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Sarkar, R., KhudaBukhsh, A.: Are chess discussions racist? an adversarial hate speech data set (student abstract). In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 15881\u201315882 (May 2021)","DOI":"10.1609\/aaai.v35i18.17937"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Swamy, S.D., Jamatia, A., Gamb\u00e4ck, B.: Studying generalisability across abusive language detection datasets. In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pp. 940\u2013950 (2019)","DOI":"10.18653\/v1\/K19-1088"},{"key":"2_CR29","unstructured":"Taori, R., et al.: Alpaca: A strong, replicable instruction-following model. Stanford Center Res. Foundation Models. https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html3(6), 7 (2023)"},{"key":"2_CR30","unstructured":"Toraman, C., \u015eahinu\u00e7, F., Yilmaz, E.H.: Large-scale hate speech detection with cross-domain transfer. arXiv preprint arXiv:2203.01111 (2022)"},{"key":"2_CR31","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"2_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Waseem, Z.: Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In: Proceedings of the First Workshop on NLP and Computational Social Science, pp. 138\u2013142 (2016)","DOI":"10.18653\/v1\/W16-5618"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Davidson, T., Warmsley, D., Weber, I.: Understanding abuse: a typology of abusive language detection subtasks. arXiv preprint arXiv:1705.09899 (2017)","DOI":"10.18653\/v1\/W17-3012"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Hovy, D.: Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In: Proceedings of the NAACL Student Research Workshop, pp. 88\u201393 (2016)","DOI":"10.18653\/v1\/N16-2013"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Thorne, J., Bingel, J.: Bridging the gaps: Multi task learning for domain transfer of hate speech detection. Online harassment, pp. 29\u201355 (2018)","DOI":"10.1007\/978-3-319-78583-7_3"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Weerasooriya, T., Dutta, S., Ranasinghe, T., Zampieri, M., Homan, C., Khudabukhsh, A.: Vicarious offense and noise audit of offensive speech classifiers: Unifying human and machine disagreement on what is offensive. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 11648\u201311668 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.713"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Wulczyn, E., Thain, N., Dixon, L.: Ex Machina: Personal attacks seen at scale. In: Proceedings of the 26th International Conference on World Wide Web, pp. 1391\u20131399 (2017)","DOI":"10.1145\/3038912.3052591"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Zampieri, M., Malmasi, S., Nakov, P., Rosenthal, S., Farra, N., Kumar, R.: Predicting the type and target of offensive posts in social media. arXiv preprint arXiv:1902.09666 (2019)","DOI":"10.18653\/v1\/N19-1144"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96962-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T07:34:12Z","timestamp":1751009652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96962-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031969614","9783031969621"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96962-1_2","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":"28 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"We caution against relying exclusively on AI-generated predictions of hate speech for high-stakes or real-world applications. Hate speech is inherently subjective and highly context-dependent; even accurate models at the aggregate level may fail to account for cultural nuance, sarcasm, or reclaimed language at the individual level. These risks are amplified when models trained in one sociocultural context are applied to another, where norms and linguistic cues differ\u00a0[]. Furthermore, the opacity of large language models and the lack of transparency in their pretraining data make it difficult to assess how sociocultural priors are encoded or reinforced. To mitigate these risks, we emphasize the need for continual in-context evaluation, supported by human oversight and participatory annotation practices that reflect the values and expectations of affected communities. Transparency, context-awareness, and sustained monitoring are essential for the responsible deployment of LLMs in hate speech detection.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Considerations"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"T\u00fcrkiye","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":"30 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}