{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:56Z","timestamp":1755794936524,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737273","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:03:27Z","timestamp":1754255007000},"page":"4682-4693","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0172-139X","authenticated-orcid":false,"given":"Xingyu","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1270-200X","authenticated-orcid":false,"given":"Tianke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2914-6527","authenticated-orcid":false,"given":"Chang","family":"Meng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7628-7257","authenticated-orcid":false,"given":"Xiaobei","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4352-4897","authenticated-orcid":false,"given":"Jinpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6227-0183","authenticated-orcid":false,"given":"Yi-Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4550-3950","authenticated-orcid":false,"given":"Shisong","family":"Tang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5608-3031","authenticated-orcid":false,"given":"Changyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0746-4376","authenticated-orcid":false,"given":"Haojie","family":"Ding","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7383-3566","authenticated-orcid":false,"given":"Kaiyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4574-4361","authenticated-orcid":false,"given":"Kaiyu","family":"Tang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2058-1609","authenticated-orcid":false,"given":"Bin","family":"Wen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5128-5649","authenticated-orcid":false,"given":"Hai-Tao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4570-5885","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0310-7751","authenticated-orcid":false,"given":"Tingting","family":"Gao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5475-2728","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3636-3618","authenticated-orcid":false,"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Unafliated, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3697349"},{"key":"e_1_3_2_2_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2016.05.051"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331262"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.alw-1.16"},{"key":"e_1_3_2_2_6_1","unstructured":"Palwasha Bibi. 2024. Legal and Ethical Challenges of Content Moderation: Balancing Privacy and Free Speech in the AI Era. (2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SocialCom.2013.21"},{"key":"e_1_3_2_2_8_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877-1901."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359276"},{"key":"e_1_3_2_2_10_1","volume-title":"Evlm: An efficient vision-language model for visual understanding. arXiv preprint arXiv:2407.14177","author":"Chen Kaibing","year":"2024","unstructured":"Kaibing Chen, Dong Shen, Hanwen Zhong, Huasong Zhong, Kui Xia, Di Xu, Wei Yuan, Yifei Hu, Bin Wen, Tianke Zhang, et al. 2024. Evlm: An efficient vision-language model for visual understanding. arXiv preprint arXiv:2407.14177 (2024)."},{"key":"e_1_3_2_2_11_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1054972.1054975"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_2_2_14_1","volume-title":"Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, and Anh Gia-Tuan Nguyen.","author":"Thi-Thuy Do Hang","year":"2019","unstructured":"Hang Thi-Thuy Do, Huy Duc Huynh, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, and Anh Gia-Tuan Nguyen. 2019. Hate speech detection on vietnamese social media text using the bidirectional-lstm model. arXiv preprint arXiv:1911.03648 (2019)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818717"},{"key":"e_1_3_2_2_16_1","volume-title":"Deep Learning Based Hate Speech Detection on Twitter. In 2023 IEEE 13th International Conference on Consumer Electronics-Berlin (ICCE-Berlin). IEEE, 1-6.","author":"Gaurav Akshat","year":"2023","unstructured":"Akshat Gaurav, Brij B Gupta, Kwok Tai Chui, Varsha Arya, and Priyanka Chaurasia. 2023. Deep Learning Based Hate Speech Detection on Twitter. In 2023 IEEE 13th International Conference on Consumer Electronics-Berlin (ICCE-Berlin). IEEE, 1-6."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-022-00951-3"},{"key":"e_1_3_2_2_18_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00061"},{"key":"e_1_3_2_2_20_1","volume-title":"Social Media Algorithms Personalize Minors' Content After a Single Session, but Not for Their Protection. Available at SSRN 4674573","author":"Hilbert Martin","year":"2023","unstructured":"Martin Hilbert, Drew P Cingel, Jingwen Zhang, Samantha L Vigil, Jane Shawcroft, Haoning Xue, Arti Thakur, and Zubair Shafiq. 2023. # BigTech@ Minors: Social Media Algorithms Personalize Minors' Content After a Single Session, but Not for Their Protection. Available at SSRN 4674573 (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146","author":"Howard Jeremy","year":"2018","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)."},{"volume-title":"The Moderation of Contentious Content on Twitter. Master's thesis","author":"Wei Hu.","key":"e_1_3_2_2_22_1","unstructured":"Wei Hu. 2023. The Moderation of Contentious Content on Twitter. Master's thesis. University of Waterloo."},{"key":"e_1_3_2_2_23_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators. arXiv preprint arXiv:2411.05854","author":"Jo Claire Wonjeong","year":"2024","unstructured":"Claire Wonjeong Jo, Miki Wesolowska, and Magdalena Wojcieszak. 2024. Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators. arXiv preprint arXiv:2411.05854 (2024)."},{"key":"e_1_3_2_2_25_1","volume-title":"Artificial Intelligence in E-commerce: a Comprehensive Analysis. Available at SSRN 4770338","author":"Joshi Meet Ashokkumar","year":"2024","unstructured":"Meet Ashokkumar Joshi. 2024. Artificial Intelligence in E-commerce: a Comprehensive Analysis. Available at SSRN 4770338 (2024)."},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464464.2464499"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v18i1.31358"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8539"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Alyssa Lees Vinh Q Tran Yi Tay Jeffrey Sorensen Jai Gupta Donald Metzler and Lucy Vasserman. 2022. A new generation of perspective api: Efficient multilingual character-level transformers. In SIGKDD.","DOI":"10.1145\/3534678.3539147"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900580"},{"key":"e_1_3_2_2_32_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692 (2019). https:\/\/api.semanticscholar.org\/CorpusID:198953378"},{"key":"e_1_3_2_2_33_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449180"},{"key":"e_1_3_2_2_35_1","volume-title":"Adapting large language models for content moderation: Pitfalls in data engineering and supervised fine-tuning. arXiv preprint arXiv:2310.03400","author":"Ma Huan","year":"2023","unstructured":"Huan Ma, Changqing Zhang, Huazhu Fu, Peilin Zhao, and Bingzhe Wu. 2023. Adapting large language models for content moderation: Pitfalls in data engineering and supervised fine-tuning. arXiv preprint arXiv:2310.03400 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.54"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-017-0462-9"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00750-4"},{"key":"e_1_3_2_2_40_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pretraining. (2018)."},{"key":"e_1_3_2_2_41_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479512"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1101"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42380-021-00105-7"},{"key":"e_1_3_2_2_46_1","unstructured":"Leandro Silva Mainack Mondal Denzil Correa Fabr\u00edcio Benevenuto and Ingmar Weber. 2016. Analyzing the targets of hate in online social media. In AAAI."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/20539517231172424"},{"key":"e_1_3_2_2_48_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_2_49_1","volume-title":"The spread of true and false news online. science 359, 6380","author":"Vosoughi Soroush","year":"2018","unstructured":"Soroush Vosoughi, Deb Roy, and Sinan Aral. 2018. The spread of true and false news online. science 359, 6380 (2018), 1146-1151."},{"key":"e_1_3_2_2_50_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Civil_law_(legal_system) [Online","author":"Wikipedia","year":"2025","unstructured":"Wikipedia contributors. 2025. Civil law (legal system) - Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Civil_law_(legal_system) [Online; accessed February 10, 2025]."},{"key":"e_1_3_2_2_51_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Common_law [Online","author":"Wikipedia","year":"2025","unstructured":"Wikipedia contributors. 2025. Common law - Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Common_law [Online; accessed February 10, 2025]."},{"key":"e_1_3_2_2_52_1","first-page":"1","article-title":"Volunteer moderators in twitch micro communities: How they get involved, the roles they play, and the emotional labor they experience","author":"Wohn Donghee Yvette","year":"2019","unstructured":"Donghee Yvette Wohn. 2019. Volunteer moderators in twitch micro communities: How they get involved, the roles they play, and the emotional labor they experience. In CHI. 1-13.","journal-title":"CHI."},{"key":"e_1_3_2_2_53_1","volume-title":"Chinese clip: Contrastive vision-language pretraining in chinese. arXiv preprint arXiv:2211.01335","author":"Yang An","year":"2022","unstructured":"An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, and Chang Zhou. 2022. Chinese clip: Contrastive vision-language pretraining in chinese. arXiv preprint arXiv:2211.01335 (2022)."},{"key":"e_1_3_2_2_54_1","volume-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding. arXiv preprint arXiv:1906.08237","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. arXiv preprint arXiv:1906.08237 (2019)."},{"key":"e_1_3_2_2_55_1","volume-title":"Systematic review: YouTube recommendations and problematic content. Internet policy review 11, 1","author":"Yesilada Muhsin","year":"2022","unstructured":"Muhsin Yesilada and Stephan Lewandowsky. 2022. Systematic review: YouTube recommendations and problematic content. Internet policy review 11, 1 (2022)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394231.3397902"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452313"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:40:54Z","timestamp":1755355254000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":57,"alternative-id":["10.1145\/3711896.3737273","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737273","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}