{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:19:01Z","timestamp":1765995541440,"version":"3.40.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:00:00Z","timestamp":1743120000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:00:00Z","timestamp":1743120000000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-03864-y","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T10:58:52Z","timestamp":1743418732000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Content Moderation of Generative AI Prompts"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0043-8013","authenticated-orcid":false,"given":"Praful","family":"Pardhi","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,28]]},"reference":[{"key":"3864_CR1","doi-asserted-by":"publisher","DOI":"10.1177\/2053951719897945","author":"R Gorwa","year":"2020","unstructured":"Gorwa R, Binns R, Katzenbach C. Algorithmic content moderation: technical and political challenges in the automation of platform governance. Big Data Soc. 2020. https:\/\/doi.org\/10.1177\/2053951719897945.","journal-title":"Big Data Soc"},{"key":"3864_CR2","doi-asserted-by":"crossref","unstructured":"Sun H, Ni W. Design and application of an AI-based text content moderation system. Scientific programming for industry 5.0: theory, applications, and technological development. 2022. https:\/\/www.hindawi.com\/journals\/sp\/2022\/2576535\/.","DOI":"10.1155\/2022\/2576535"},{"key":"3864_CR3","unstructured":"Brown B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A,Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D. Language models are few-shot learners. arXiv. 2020. https:\/\/arxiv.org\/abs\/2005.14165."},{"key":"3864_CR4","unstructured":"Singh G, Deng F, Ahn S. Illiterate DALL-e learns to compose. arXiv. 2021. https:\/\/arxiv.org\/abs\/2110.11405."},{"key":"3864_CR5","doi-asserted-by":"crossref","unstructured":"Papadopoulos D, Karalis VD. Variational autoencoders for data augmentation in clinical studie. Appl Sci. 2023. https:\/\/www.mdpi.com\/2076-3417\/13\/15\/8793.","DOI":"10.3390\/app13158793"},{"key":"3864_CR6","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.inffus.2022.10.017","volume":"91","author":"T Zhou","year":"2023","unstructured":"Zhou T, Li Q, Lu H, Cheng Q, Zhang X. Gan review: models and medical image fusion applications. Inf Fusion. 2023;91:134\u201348.","journal-title":"Inf Fusion"},{"key":"3864_CR7","doi-asserted-by":"publisher","unstructured":"Liu V, Chilton L. Design guidelines for prompt engineering text-to-image generative models. In: CHI Conference on human factors in computing systems. 2022. https:\/\/doi.org\/10.1145\/3491102.3501825.","DOI":"10.1145\/3491102.3501825"},{"key":"3864_CR8","unstructured":"Jones B, Jones R, Luger E. Generative AI & journalism: a rapid risk-based review. Edinburgh Research Explorer. 2023. https:\/\/www.research.ed.ac.uk\/en\/publications\/generative-ai-amp-journalism-a-rapid-risk-based-review."},{"key":"3864_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10777-x","author":"M Elasri","year":"2022","unstructured":"Elasri M, Elharrouss O, Al-Maadeed S, Tairi H. Image generation: a review. Neural Process Lett. 2022. https:\/\/doi.org\/10.1007\/s11063-022-10777-x.","journal-title":"Neural Process Lett"},{"key":"3864_CR10","unstructured":"Chang Y, Wang X, Wang J, Wu Y, Yang L, Zhu K, Chen H, Yi X, Wang, C, Wang Y, Ye W, Zhang Y, Chang Y, Yu PS, Yang Q, Xie X. A survey on evaluation of large language models. arXiv. 2023. https:\/\/arxiv.org\/abs\/2307.03109."},{"key":"3864_CR11","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozi`ere B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A, Grave E, Lample G. Llama: open and efficient foundation language models. arXiv. 2023. https:\/\/arxiv.org\/abs\/2302.13971."},{"key":"3864_CR12","doi-asserted-by":"crossref","unstructured":"Croitoru F-A, Hondru V, Ionescu RT, Shah M. Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell. 2023. https:\/\/ieeexplore.ieee.org\/abstract\/document\/10081412\/.","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"3864_CR13","doi-asserted-by":"publisher","unstructured":"Binns R, Veale M, Kleek MV, Shadbolt N. Like trainer, like bot? Inheritance of bias in algorithmic content moderation. In: International conference on social informatics. 2017. https:\/\/doi.org\/10.1007\/978-3-319-67256-432.","DOI":"10.1007\/978-3-319-67256-432"},{"key":"3864_CR14","doi-asserted-by":"publisher","unstructured":"Son Lew B, Choi K, Baek Y, Choi S, Shin B, Ha S, Chang B. Reliable decision from multiple subtasks through threshold optimization: content moderation in the wild. In: Proceedings of the sixteenth ACM international conference on web search and data mining. 2023. https:\/\/doi.org\/10.1145\/3539597.3570439.","DOI":"10.1145\/3539597.3570439"},{"key":"3864_CR15","doi-asserted-by":"publisher","unstructured":"Gulati G, Jha HA, Jain R, Sharma M, Chaudhary V. Content moderation system using machine learning techniques. Lecture notes in networks and systems. 2023. https:\/\/doi.org\/10.1007\/978-981-99-4071-458.","DOI":"10.1007\/978-981-99-4071-458"},{"key":"3864_CR16","doi-asserted-by":"publisher","unstructured":"Hettiachchi D, Goncalves J. Towards effective crowd-powered online content moderation. In: Proceedings of the 31st australian conference on human-computer-interaction. 2019. https:\/\/doi.org\/10.1145\/3369457.3369491.","DOI":"10.1145\/3369457.3369491"},{"key":"3864_CR17","unstructured":"Hao S, Kumar P, Laszlo S, Poddar S, Radharapu B, Shelby R. Safety and fairness for content moderation in generative models. arXiv. 2023. https:\/\/arxiv.org\/abs\/2306.06135."},{"key":"3864_CR18","doi-asserted-by":"publisher","DOI":"10.1177\/2053951720943234","author":"T Gillespie","year":"2020","unstructured":"Gillespie T. Content moderation, AI, and the question of scale. Big Data Soc. 2020. https:\/\/doi.org\/10.1177\/2053951720943234.","journal-title":"Big Data Soc"},{"key":"3864_CR19","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1007\/s12119-020-09790-w","volume":"25","author":"TD Oliva","year":"2021","unstructured":"Oliva TD, Antonialli DM, Gomes A. Fighting hate speech, silencing drag queens? Artificial intelligence in content moderation and risks to LGBTQ voices online. Sexual Cult. 2021;25:700\u201332.","journal-title":"Sexual Cult"},{"key":"3864_CR20","doi-asserted-by":"crossref","first-page":"105374","DOI":"10.1016\/j.clsr.2019.105374","volume":"36","author":"GD Gregorio","year":"2020","unstructured":"Gregorio GD. Democratising online content moderation: a constitutional framework. Comput Law Secur Rev. 2020;36:105374.","journal-title":"Comput Law Secur Rev"},{"key":"3864_CR21","doi-asserted-by":"crossref","unstructured":"Zhu W, Gong H, Bansal R, Weinberg Z, Christin N, Fanti G, Bhat S. Self-supervised euphemism detection and identification for content moderation. In: IEEE symposium on security and privacy (SP). 2021. https:\/\/ieeexplore.ieee.org\/abstract\/document\/9519422.","DOI":"10.1109\/SP40001.2021.00075"},{"key":"3864_CR22","unstructured":"Akyon FC, Temizel A. Deep architectures for content moderation and movie content rating. arXiv. 2022. https:\/\/arxiv.org\/abs\/2212.04533."},{"key":"3864_CR23","doi-asserted-by":"publisher","unstructured":"Hacker P, Engel A, Mauer M. Regulating chatgpt and other large generative ai models. ACM FAccT. 2023. https:\/\/doi.org\/10.1145\/3593013.3594067.","DOI":"10.1145\/3593013.3594067"},{"key":"3864_CR24","first-page":"121","volume":"3","author":"PP Ray","year":"2023","unstructured":"Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber Phys Syst. 2023;3:121\u201354.","journal-title":"Internet Things Cyber Phys Syst"},{"key":"3864_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s10956-023-10039-y","author":"G Cooper","year":"2023","unstructured":"Cooper G. Examining science education in chatgpt: an exploratory study of generative artificial intelligence. J Sci Educ Technol. 2023. https:\/\/doi.org\/10.1007\/s10956-023-10039-y.","journal-title":"J Sci Educ Technol"},{"key":"3864_CR26","doi-asserted-by":"publisher","unstructured":"Ghafouri V, Agarwal V, Zhang Y, Sastry N, Such J, Suarez-Tangil G. AI in the gray: exploring moderation policies in dialogic large language models vs. human answers in controversial topics. In: ACM international conference on information and knowledge management. 2023. https:\/\/doi.org\/10.1145\/3583780.3614777.","DOI":"10.1145\/3583780.3614777"},{"key":"3864_CR27","unstructured":"Penedo G, Malartic Q, Hesslow D, Cojocaru R, Cappelli A, Alobeidli H, Pannier B, Almazrouei E, Launay J. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv. 2023. https:\/\/arxiv.org\/pdf\/2306.01116.pdf?trk=publicpostcomment-text."},{"key":"3864_CR28","doi-asserted-by":"crossref","unstructured":"Dautov R, Husom EJ, Sen S, Song H. Towards community-driven generative AI. In: Position papers of the 18th conference on computer science and intelligence systems. 2023. https:\/\/annals-csis.org\/proceedings\/2023\/pliks\/position.pdf#page=52","DOI":"10.15439\/2023F5494"},{"key":"3864_CR29","doi-asserted-by":"crossref","unstructured":"Pavlopoulos J, Malakasiotis P, Androutsopoulos I. Deeper attention to abusive user content moderation. In: Proceedings of the 2017 conference on empirical methods in natural language processing. 2017. https:\/\/aclanthology.org\/D17-1117\/.","DOI":"10.18653\/v1\/D17-1117"},{"key":"3864_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-024-00250-1","author":"E Ferrara","year":"2024","unstructured":"Ferrara E. Genai against humanity: nefarious applications of generative artificial intelligence and large language models. J Comput Soc Sci. 2024. https:\/\/doi.org\/10.1007\/s42001-024-00250-1.","journal-title":"J Comput Soc Sci"},{"key":"3864_CR31","doi-asserted-by":"publisher","unstructured":"Vaccaro K, Xiao Z, Hamilton K, Karahalios K. Contestability for content moderation. In: Proceedings of the ACM on human-computer interaction. 2021. https:\/\/doi.org\/10.1145\/3476059.","DOI":"10.1145\/3476059"},{"key":"3864_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-022-00951-3","author":"VU Gongane","year":"2022","unstructured":"Gongane VU, Mousami V, Munot ADA. Detection and moderation of detrimental content on social media platforms: current status and future directions. Soc Netw Anal Min. 2022. https:\/\/doi.org\/10.1007\/s13278-022-00951-3.","journal-title":"Soc Netw Anal Min"},{"key":"3864_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s12525-023-00680-1","author":"L Banh","year":"2023","unstructured":"Banh L, Strobel G. Generative artificial intelligence. Electron Markets. 2023. https:\/\/doi.org\/10.1007\/s12525-023-00680-1.","journal-title":"Electron Markets"},{"key":"3864_CR34","doi-asserted-by":"crossref","unstructured":"Markov T, Zhang C, Agarwal S, Nekoul FE, Lee T, Adler S, Jiang A, Weng L. A holistic approach to undesired content detection in the real world. Proceedings of the AAAI conference on artificial intelligence. 2023. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/26752.","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"3864_CR35","doi-asserted-by":"publisher","DOI":"10.1177\/2053951720932296","author":"N Elkin-Koren","year":"2020","unstructured":"Elkin-Koren N. Contesting algorithms: restoring the public interest in content filtering by artificial intelligence. Big Data Soc. 2020. https:\/\/doi.org\/10.1177\/2053951720932296.","journal-title":"Big Data Soc"},{"key":"3864_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-11968-3","author":"D Karabulut","year":"2022","unstructured":"Karabulut D, Ozcinar C, Anbarjafari G. Automatic content moderation on social media. Multimedia Tools Appl. 2022. https:\/\/doi.org\/10.1007\/s11042-022-11968-3.","journal-title":"Multimedia Tools Appl"},{"key":"3864_CR37","doi-asserted-by":"crossref","unstructured":"Partadiredja RA, Serrano CE, Ljubenkov D. AI or human: the socioethical implications of AI-generated media content. In: 13th CMI conference on cybersecurity and privacy (CMI) digital transformation potentials and challenges (51275). 2020. https:\/\/ieeexplore.ieee.org\/abstract\/document\/9322673.","DOI":"10.1109\/CMI51275.2020.9322673"},{"key":"3864_CR38","doi-asserted-by":"crossref","unstructured":"Macrayo G, Casin\u02dco W, Dalangin J, Gahoy JG, Reyes AC, Vitto C, Abisado M, Huyo-a SL, Sampedro GA. Please be nice: a deep learning based approach to content moderation of internet memes. In: International conference on electronics, information, and communication (ICEIC). 2023. https:\/\/ieeexplore.ieee.org\/abstract\/document\/10049865.","DOI":"10.1109\/ICEIC57457.2023.10049865"},{"key":"3864_CR39","doi-asserted-by":"crossref","unstructured":"Banko M, MacKeen B, Ray L. A unified taxonomy of harmful content. In: Proceedings of the fourth workshop on online abuse and harms. 2020. https:\/\/aclanthology.org\/2020.alw-1.16\/.","DOI":"10.18653\/v1\/2020.alw-1.16"},{"key":"3864_CR40","doi-asserted-by":"publisher","unstructured":"Scheuerman MK, Jiang JA, Fiesler C, Brubaker J. A framework of severity for harmful content online. In: Proceedings of the ACM on human-computer interaction, vol 5, Issue CSCW2. 2021. https:\/\/doi.org\/10.1145\/3479512.","DOI":"10.1145\/3479512"},{"key":"3864_CR41","doi-asserted-by":"publisher","DOI":"10.1145\/360339","author":"A Arora","year":"2023","unstructured":"Arora A, Nakov P, Hardalov M, Sarwar SM, Nayak V, Dinkov Y, Zlatkova D, Dent K, Bhatawdekar A, Bouchard G, Augenstein I. Detecting harmful content on online platforms: what platforms need vs. where research efforts go. ACM Comput Surv. 2023. https:\/\/doi.org\/10.1145\/360339.","journal-title":"ACM Comput Surv"},{"key":"3864_CR42","unstructured":"Hive moderation. https:\/\/hivemoderation.com\/."},{"key":"3864_CR43","unstructured":"Zeng W, Liu Y, Mullins R, Peran L, Fernandez J, Harkous H, Narasimhan K, Proud D, Kumar P, Radharapu B, Sturman O, Wahltinez O. Shieldgemma: generative AI content moderation based on gemma. arXiv. 2024. https:\/\/arxiv.org\/pdf\/2407.21772."},{"key":"3864_CR44","doi-asserted-by":"publisher","unstructured":"Wang W, Huang J, Chen C, Gu J, Zhang J, Wu W, He P, Lyu M. Validating multimedia content moderation software via semantic fusion. In: ISSTA 2023: proceedings of the 32nd ACM SIGSOFT international symposium on software testing and analysis. 2023. https:\/\/doi.org\/10.1145\/3597926.3598079.","DOI":"10.1145\/3597926.3598079"},{"key":"3864_CR45","doi-asserted-by":"crossref","unstructured":"Ye Z, Geng Y, Chen J, Chen J, Xu X, Zheng S, Wang F, Zhang J, Chen H. Zero-shot text classification via reinforced self-training. In: Proceedings of the 58th annual meeting of the association for computational linguistics. 2020. https:\/\/aclanthology.org\/2020.acl-main.272\/.","DOI":"10.18653\/v1\/2020.acl-main.272"},{"key":"3864_CR46","unstructured":"Open instruction dataset. https:\/\/laion.ai\/blog\/oig-dataset\/."},{"key":"3864_CR47","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv. 2019. https:\/\/arxiv.org\/abs\/1910.13461.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"3864_CR48","unstructured":"Facebook BART model. https:\/\/huggingface.co\/facebook\/bart-large-mnli."},{"key":"3864_CR49","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv. 2019. https:\/\/arxiv.org\/abs\/1810.04805."},{"key":"3864_CR50","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. arXiv. 2017. https:\/\/arxiv.org\/abs\/1706.03762."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03864-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-03864-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03864-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T10:59:10Z","timestamp":1743418750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-03864-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,28]]},"references-count":50,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["3864"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-03864-y","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2025,3,28]]},"assertion":[{"value":"7 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 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":"No competing interests for this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving human and \/or animals"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}],"article-number":"329"}}