{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T23:05:41Z","timestamp":1778108741082,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032131836","type":"print"},{"value":"9783032131843","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\/978-3-032-13184-3_24","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:58:49Z","timestamp":1767322729000},"page":"386-403","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Safer AI Moderation: Evaluating LLM Moderators Through a\u00a0Unified Benchmark Dataset and\u00a0Advocating a\u00a0Human-First Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1865-1800","authenticated-orcid":false,"given":"Naseem","family":"Machlovi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-5078","authenticated-orcid":false,"given":"Maryam","family":"Saleki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8498-1086","authenticated-orcid":false,"given":"Innocent","family":"Ababio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6540-3415","authenticated-orcid":false,"given":"Ruhul","family":"Amin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"24_CR1","unstructured":"Abdin, M., et\u00a0al.: Phi-4 technical report. arXiv preprint arXiv:2412.08905 (2024)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Anastasopoulos, L.J., Williams, J.R.: A scalable machine learning approach for measuring violent and peaceful forms of political protest participation with social media data. Plos one (2019)","DOI":"10.1371\/journal.pone.0212834"},{"key":"24_CR3","unstructured":"Mathew, B., Saha, P., H.T.e.a.: Threat, abuse, and hate detection on social media: a dynamic thresholding approach. In: International AAAI Conference on Web and Social Media (2021)"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Breitwieser, K.: Can contextualizing user embeddings improve sarcasm and hate speech detection? In: Bamman, D., Hovy, D., Jurgens, D., Keith, K., O\u2019Connor, B., Volkova, S. (eds.) Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), pp. 126\u2013139. Abu Dhabi, UAE, November 2022. https:\/\/doi.org\/10.18653\/v1\/2022.nlpcss-1.14","DOI":"10.18653\/v1\/2022.nlpcss-1.14"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Offensivelang: a community based implicit offensive language dataset (2024)","DOI":"10.1109\/ACCESS.2024.3513220"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Demszky, D., Movshovitz-Attias, Y.: Goemotions: a dataset of fine-grained emotions. In: 58th Annual Meeting of the Association for Computational Linguistics (ACL) (2020)","DOI":"10.18653\/v1\/2020.acl-main.372"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: ABERT: pre-training of deep bidirectional transformers for language understanding, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423\/","DOI":"10.18653\/v1\/N19-1423"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Barbieri, F., Camacho-Collados, J., L.E.A., Neves, L.: Tweeteval: unified benchmark and comparative evaluation for tweet classification. In: Findings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.148"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Gehman, S., Gururangan, S., Sap, M., Choi, Y., Smith, N.A.: RealToxicityPrompts: evaluating neural toxic degeneration in language models (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"24_CR11","unstructured":"Ghosh, S., Varshney, P., Galinkin, E., Parisien, C.: Aegis: Online adaptive ai content safety moderation with ensemble of llm experts (2024)"},{"key":"24_CR12","unstructured":"Gibert, O.D., Perez, N., Garc\u00eda-Pablos, A., Cuadros, M.: Hate speech dataset from a white supremacy forum, September 2018"},{"key":"24_CR13","unstructured":"Han, S., et al.: WildGuard: open one-stop moderation tools for safety risks, jailbreaks, and refusals of LLMs (2024)"},{"key":"24_CR14","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2021)"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Hom, C.: The semantics of racial epithets. J. Philos. (2008)","DOI":"10.5840\/jphil2008105834"},{"key":"24_CR16","unstructured":"Inan, H., et al.: Llama guard: Llm-based input-output safeguard for human-ai conversations (2023)"},{"key":"24_CR17","unstructured":"J.\u00a0Dillion, A.G.E.A.: Adversarial content generation for robustness testing in large language models (2023)"},{"key":"24_CR18","unstructured":"Kurrek, J., H.M.S., Ruths, D.: Towards a comprehensive taxonomy and large-scale annotated corpus for online slur usage. Association for Computational Linguistics"},{"key":"24_CR19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2902","volume-title":"When does a Compliment Become Sexist? Analysis and Classification of Ambivalent Sexism Using Twitter Data","author":"A Jha","year":"2017","unstructured":"Jha, A., Mamidi, R.: When does a Compliment Become Sexist? Analysis and Classification of Ambivalent Sexism Using Twitter Data. Vancouver, Canada (2017)"},{"key":"24_CR20","unstructured":"Ji, J., et al.: Beavertails: towards improved safety alignment of llm via a human-preference dataset. In: Advances in Neural Information Processing Systems (2023)"},{"key":"24_CR21","unstructured":"Jiang, L., et\u00a0al.: Can machines learn morality? the delphi experiment (2021)"},{"key":"24_CR22","unstructured":"Jigsaw and Google: Jigsaw toxic comments dataset (2018)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Jin, Y., Wanner, L., Shvets, A.: Gpt-hatecheck: can llms write better functional tests for hate speech detection? (2024)","DOI":"10.63317\/457md257uym3"},{"key":"24_CR24","unstructured":"Kennedy, C.J., Bacon, G., Sahn, A., Vacano, C.V.: Constructing interval variables via faceted Rasch measurement and multitask deep learning: a hate speech application (2020)"},{"key":"24_CR25","unstructured":"Li, X., et al.: Alpacaeval: an automatic evaluator of instruction-following models (2023)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Liao, S.M.: Ethics of Artificial Intelligence. Oxford University Press (2020)","DOI":"10.1093\/oso\/9780190905033.001.0001"},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. Association for Computational Linguistics, Hong Kong, China, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-1387, https:\/\/aclanthology.org\/D19-1387\/","DOI":"10.18653\/v1\/D19-1387"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Mathew, B., Saha, P., Yimam, S.M., Biemann, C., Goyal, P., Mukherjee, A.: HateXplain: a benchmark dataset for explainable hate speech detection (2022)","DOI":"10.1609\/aaai.v35i17.17745"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Maynez, J., Narayan, S., Bohnet, B., McDonald, R.: On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661 (2020)","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"24_CR30","unstructured":"OpenAI: Openai moderation api (2025) https:\/\/platform.openai.com\/docs\/guides\/moderation, Accessed 08 Jan 2025"},{"key":"24_CR31","unstructured":"P.\u00a0R\u00f6ttger, B.\u00a0Vidgen, D.N.Z.W.H.M., Pierrehumbert, J.B.: Hatecheck: functional tests for hate speech detection models. arXiv preprint arXiv:2012.15606 (2020)"},{"key":"24_CR32","unstructured":"Sachdeva, P., R.B., Bacon, G.: The measuring hate speech corpus: Leveraging rasch measurement theory for data perspectivism. Eur. Lang. Resour. Assoc"},{"key":"24_CR33","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog"},{"key":"24_CR34","unstructured":"Rosenthal, S., Atanasova, P., Karadzhov, G., Zampieri, M., Nakov, P.: Solid: a large-scale semi-supervised dataset for offensive language identification"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"R\u00f6ttger, P., Vidgen, B., Nguyen, D., Waseem, Z., Margetts, H., Pierrehumbert, J.B.: Hatecheck: functional tests for hate speech detection models (2020)","DOI":"10.18653\/v1\/2021.acl-long.4"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"R\u00f6ttger, P., Pernisi, F., Vidgen, B., Hovy, D.: Safetyprompts: a systematic review of open datasets for evaluating and improving large language model safety (2025). https:\/\/arxiv.org\/abs\/2404.05399","DOI":"10.1609\/aaai.v39i26.34975"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Samory, M., Sen, I., Kohne, J., Fl\u00f6ck, F., Wagner, C.: \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 (2021)","DOI":"10.1609\/icwsm.v15i1.18085"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Sap, M., Card, D., Gabriel, S.: The risk of racial bias in hate speech detection. ACL (2019)","DOI":"10.18653\/v1\/P19-1163"},{"key":"24_CR39","unstructured":"Sap, M., Gabriel, S., Qin, L., Jurafsky, D., Smith, N.A., Choi, Y.: Social bias frames: reasoning about social and power implications of language. Association for Computational Linguistics"},{"key":"24_CR40","unstructured":"Schwitzgebel, E., Garza, M.: Designing ai with rights, consciousness, self-respect, and freedom (2023)"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Sheng, E., Chang, K.W., Natarajan, P., Peng, N.: The woman worked as a babysitter: on biases in language generation (2019)","DOI":"10.18653\/v1\/D19-1339"},{"key":"24_CR42","unstructured":"Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. Trans. Mach. Learn. Res. (2023)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Tilly, C.: The Politics of Collective Violence. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511819131"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Van\u00a0Deth, J.W.: A conceptual map of political participation (2014)","DOI":"10.1057\/ap.2014.6"},{"key":"24_CR45","unstructured":"Vidgen, B., Derczynski, L.: Challenges in multilingual content moderation (2021)"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Hovy, D.: Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. San Diego, California (2016)","DOI":"10.18653\/v1\/N16-2013"},{"key":"24_CR47","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 (2019)","DOI":"10.18653\/v1\/N19-1144"},{"key":"24_CR48","unstructured":"Zeng, W., Liu, Y., Mullins, R.: Shieldgemma: generative ai content moderation based on gemma (2024)"},{"key":"24_CR49","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena (2023)"}],"container-title":["Lecture Notes in Computer Science","HCI International 2025 \u2013 Late Breaking Papers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-13184-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:23:25Z","timestamp":1775190205000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-13184-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032131836","9783032131843"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-13184-3_24","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gothenburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}