{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T04:05:55Z","timestamp":1749873955514,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","funder":[{"name":"Student Summer Research Program 2024 of FIT CTU in Prague"},{"DOI":"10.13039\/100018701","name":"HORIZON EUROPE Food, Bioeconomy, Natural Resources, Agriculture and Environment","doi-asserted-by":"publisher","award":["101136910"],"award-info":[{"award-number":["101136910"]}],"id":[{"id":"10.13039\/100018701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,16]]},"DOI":"10.1145\/3699682.3728329","type":"proceedings-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T13:05:37Z","timestamp":1749819937000},"page":"329-334","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Risks in Marketplace Semantic Search: A Dataset for Harmful and Sensitive Query Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4407-2260","authenticated-orcid":false,"given":"Filip","family":"Spacek","sequence":"first","affiliation":[{"name":"Czech Technical University, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2638-9969","authenticated-orcid":false,"given":"Vojtech","family":"Vancura","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, Czech Technical University, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1433-0089","authenticated-orcid":false,"given":"Pavel","family":"Kordik","sequence":"additional","affiliation":[{"name":"Czech Technical University, Prague, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2020. Information quality & content moderation. https:\/\/storage.googleapis.com\/gweb-uniblog-publish-prod\/documents\/Info_quality_content_moderation-whie_paper-UPDATED.pdf"},{"key":"e_1_3_3_2_3_2","unstructured":"Nouar AlDahoul Myles Joshua\u00a0Toledo Tan Harishwar\u00a0Reddy Kasireddy and Yasir Zaki. 2024. Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text Images and Videos. arxiv:https:\/\/arXiv.org\/abs\/2411.17123\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2411.17123"},{"key":"e_1_3_3_2_4_2","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova DasSarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan Nicholas Joseph Saurav Kadavath Jackson Kernion Tom Conerly Sheer El-Showk Nelson Elhage Zac Hatfield-Dodds Danny Hernandez Tristan Hume Scott Johnston Shauna Kravec Liane Lovitt Neel Nanda Catherine Olsson Dario Amodei Tom Brown Jack Clark Sam McCandlish Chris Olah Ben Mann and Jared Kaplan. 2022. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arxiv:https:\/\/arXiv.org\/abs\/2204.05862\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2204.05862"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Federico Bianchi Stefanie\u00a0Anja Hills Patricia Rossini Dirk Hovy Rebekah Tromble and Nava Tintarev. 2022. \"It\u2019s Not Just Hate\u201d: A Multi-Dimensional Perspective on Detecting Harmful Speech Online. arxiv:https:\/\/arXiv.org\/abs\/2210.15870\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2210.15870","DOI":"10.18653\/v1\/2022.emnlp-main.553"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4520057"},{"key":"e_1_3_3_2_7_2","unstructured":"cjadams Daniel Borkan inversion Jeffrey Sorensen Lucas Dixon Lucy Vasserman and nithum. 2019. Jigsaw Unintended Bias in Toxicity Classification. https:\/\/kaggle.com\/competitions\/jigsaw-unintended-bias-in-toxicity-classification. Kaggle."},{"key":"e_1_3_3_2_8_2","unstructured":"cjadams Jeffrey Sorensen Julia Elliott Lucas Dixon Mark McDonald nithum and Will Cukierski. 2017. Toxic Comment Classification Challenge. https:\/\/kaggle.com\/competitions\/jigsaw-toxic-comment-classification-challenge. Kaggle."},{"key":"e_1_3_3_2_9_2","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arxiv:https:\/\/arXiv.org\/abs\/2401.08281\u00a0[cs.LG]"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594067"},{"key":"e_1_3_3_2_11_2","unstructured":"Laura Hanu and Unitary team. 2020. Detoxify. Github. https:\/\/github.com\/unitaryai\/detoxify."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Weiming Hu Ou Wu Zhouyao Chen Zhouyu Fu and Steve Maybank. 2007. Recognition of Pornographic Web Pages by Classifying Texts and Images. IEEE Transactions on Pattern Analysis and Machine Intelligence 29 6 (2007) 1019\u20131034. 10.1109\/TPAMI.2007.1133","DOI":"10.1109\/TPAMI.2007.1133"},{"key":"e_1_3_3_2_13_2","unstructured":"Yangsibo Huang Samyak Gupta Mengzhou Xia Kai Li and Danqi Chen. 2023. Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation. arxiv:https:\/\/arXiv.org\/abs\/2310.06987\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.06987"},{"key":"e_1_3_3_2_14_2","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine and Madian Khabsa. 2023. Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations. arxiv:https:\/\/arXiv.org\/abs\/2312.06674\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2312.06674"},{"key":"e_1_3_3_2_15_2","unstructured":"Ian Kivlichan Jeffrey Sorensen Julia Elliott Lucy Vasserman Martin G\u00f6rner and Phil Culliton. 2020. Jigsaw Multilingual Toxic Comment Classification. https:\/\/kaggle.com\/competitions\/jigsaw-multilingual-toxic-comment-classification. Kaggle."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"P.Y. Lee S.C. Hui and A.C.M. Fong. 2002. Neural networks for web content filtering. IEEE Intelligent Systems 17 5 (2002) 48\u201357. 10.1109\/MIS.2002.1039832","DOI":"10.1109\/MIS.2002.1039832"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Lingyao Li Lizhou Fan Shubham Atreja and Libby Hemphill. 2024. \u201cHOT\u201d ChatGPT: The Promise of ChatGPT in Detecting and Discriminating Hateful Offensive and Toxic Comments on Social Media. ACM Trans. Web 18 2 Article 30 (March 2024) 36\u00a0pages. 10.1145\/3643829","DOI":"10.1145\/3643829"},{"key":"e_1_3_3_2_18_2","unstructured":"Zi Lin Zihan Wang Yongqi Tong Yangkun Wang Yuxin Guo Yujia Wang and Jingbo Shang. 2023. ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation. arxiv:https:\/\/arXiv.org\/abs\/2310.17389\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.17389"},{"key":"e_1_3_3_2_19_2","unstructured":"Chris\u00a0Yuhao Liu Liang Zeng Jiacai Liu Rui Yan Jujie He Chaojie Wang Shuicheng Yan Yang Liu and Yahui Zhou. 2024. Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs. arxiv:https:\/\/arXiv.org\/abs\/2410.18451\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2410.18451"},{"key":"e_1_3_3_2_20_2","unstructured":"Todor Markov Chong Zhang Sandhini Agarwal Tyna Eloundou Teddy Lee Steven Adler Angela Jiang and Lilian Weng. 2022. A Holistic Approach to Undesired Content Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.03274 (2022)."},{"key":"e_1_3_3_2_21_2","unstructured":"Nvidia : Bo Adler Niket Agarwal Ashwath Aithal Dong\u00a0H. Anh Pallab Bhattacharya Annika Brundyn Jared Casper Bryan Catanzaro Sharon Clay Jonathan Cohen Sirshak Das Ayush Dattagupta Olivier Delalleau Leon Derczynski Yi Dong Daniel Egert Ellie Evans Aleksander Ficek Denys Fridman Shaona Ghosh Boris Ginsburg Igor Gitman Tomasz Grzegorzek Robert Hero Jining Huang Vibhu Jawa Joseph Jennings Aastha Jhunjhunwala John Kamalu Sadaf Khan Oleksii Kuchaiev Patrick LeGresley Hui Li Jiwei Liu Zihan Liu Eileen Long Ameya\u00a0Sunil Mahabaleshwarkar Somshubra Majumdar James Maki Miguel Martinez Maer\u00a0Rodrigues de Melo Ivan Moshkov Deepak Narayanan Sean Narenthiran Jesus Navarro Phong Nguyen Osvald Nitski Vahid Noroozi Guruprasad Nutheti Christopher Parisien Jupinder Parmar Mostofa Patwary Krzysztof Pawelec Wei Ping Shrimai Prabhumoye Rajarshi Roy Trisha Saar Vasanth Rao\u00a0Naik Sabavat Sanjeev Satheesh Jane\u00a0Polak Scowcroft Jason Sewall Pavel Shamis Gerald Shen Mohammad Shoeybi Dave Sizer Misha Smelyanskiy Felipe Soares Makesh\u00a0Narsimhan Sreedhar Dan Su Sandeep Subramanian Shengyang Sun Shubham Toshniwal Hao Wang Zhilin Wang Jiaxuan You Jiaqi Zeng Jimmy Zhang Jing Zhang Vivienne Zhang Yian Zhang and Chen Zhu. 2024. Nemotron-4 340B Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2406.11704\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.11704"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13059-5_5"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Stephen\u00a0E Robertson Steve Walker Susan Jones Micheline\u00a0M Hancock-Beaulieu Mike Gatford et\u00a0al. 1995. Okapi at TREC-3. Nist Special Publication Sp 109 (1995) 109.","DOI":"10.6028\/NIST.SP.500-225.routing-city"},{"key":"e_1_3_3_2_25_2","unstructured":"Patrick Schramowski Manuel Brack Bj\u00f6rn Deiseroth and Kristian Kersting. 2023. Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2211.05105\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.05105"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Bernd\u00a0Carsten Stahl and Damian Eke. 2024. The ethics of ChatGPT \u2013 Exploring the ethical issues of an emerging technology. International Journal of Information Management 74 (2024) 102700. 10.1016\/j.ijinfomgt.2023.102700","DOI":"10.1016\/j.ijinfomgt.2023.102700"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Maronikolakis A. & Wisiorek\u00a0A. Udupa S.2023. Ethical scaling for content moderation: Extreme speech and the (in)significance\u00a0 of artificial intelligence. Big Data & Society 10(1) (2023). 10.1177\/20539517231172424","DOI":"10.1177\/20539517231172424"},{"key":"e_1_3_3_2_28_2","unstructured":"Aleksandra Urman Aniko Hannak and Mykola Makhortykh. 2023. User Attitudes to Content Moderation in Web Search. arxiv:https:\/\/arXiv.org\/abs\/2310.03458\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2310.03458"},{"key":"e_1_3_3_2_29_2","unstructured":"Benjamin Warner Antoine Chaffin Benjamin Clavi\u00e9 Orion Weller Oskar Hallstr\u00f6m Said Taghadouini Alexis Gallagher Raja Biswas Faisal Ladhak Tom Aarsen Nathan Cooper Griffin Adams Jeremy Howard and Iacopo Poli. 2024. Smarter Better Faster Longer: A Modern Bidirectional Encoder for Fast Memory Efficient and Long Context Finetuning and Inference. arxiv:https:\/\/arXiv.org\/abs\/2412.13663\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.13663"}],"event":{"name":"UMAP '25: 33rd ACM Conference on User Modeling, Adaptation and Personalization","location":"New York City USA","acronym":"UMAP '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3699682.3728329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T13:09:31Z","timestamp":1749820171000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3699682.3728329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":28,"alternative-id":["10.1145\/3699682.3728329","10.1145\/3699682"],"URL":"https:\/\/doi.org\/10.1145\/3699682.3728329","relation":{},"subject":[],"published":{"date-parts":[[2025,6,13]]},"assertion":[{"value":"2025-06-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}