Elamur Research⌕
☰
home / papers / 2025 / AraSafe: Benchmarking Safety in Arabic LLMs

AraSafe: Benchmarking Safety in Arabic LLMs

Paper · 2025 · Hamdy Mubarak, Abubakr Mohamed and Majd Hawasly

Summary

Arabic has lacked a large safety benchmark built from genuine user input. Existing resources are mostly English or Chinese, and the Arabic ones are small, translated, or limited to a few labels such as hate or abuse. AraSafe addresses this gap. Recruited speakers from several Arab countries interacted with Arabic LLMs in MSA, dialects and English and produced over 120K prompts. From these, 12K were randomly drawn and labelled by two experts into one safe class and eight harm classes, with every disagreement resolved by hand. Harmful prompts make up only about a tenth of the natural data, so the authors also had GPT-4o produce 12K extra harmful prompts using engineered prompting strategies. They show that this synthetic data helps when fine-tuning BERT-based harm classifiers. They then tested Arabic-centric models (Jais, AceGPT, Allam, Fanar) and multilingual models (Llama-3, Gemma-2, Qwen3) in the 7–13B range on detecting harmful prompts, with GPT-4o as an upper reference. Most of these models showed weaknesses in spotting unsafe content. The authors argue that safety needs culturally grounded evaluation, and that the same recipe could transfer to other low-resource languages.

Key points

  • 110 vetted participants (mostly Egyptian, 62% female) submitted over 120K prompts across three months. A random 10% sample of 12K was annotated and released at github.com/qcri/AraSafe-benchmark.
  • Label distribution: about 89.6% "Safe/Not Harmful". The largest harm classes are Illegal Activities (3.92%), Violence or Harm (2.45%) and Privacy Violation (1.36%), while Terrorism/Extremism and Hate Speech each sit around 0.68%.
  • The two annotators agreed 97% of the time on the binary safe/harmful split, but only 82% on the nine-way categories.
  • The ASAD dialect identifier tagged 84% of prompts as MSA, with the remainder spread over Gulf, Levantine, North African and Nile Valley varieties. A manual check of 500 prompts found roughly 90% MSA.
  • Models evaluated were Jais-13B, AceGPT-v2-8B, Allam-7B, Fanar-1-9B, Llama3.1-8B, Gemma-2-9B, Qwen3-8B and fine-tuned BERT classifiers, with GPT-4o as the upper bound.

Interesting ideas

  • I1. Reporting agreement at both coarse and fine granularity shows where the real ambiguity lies: humans rarely dispute whether something is harmful, but often dispute which kind it is.
  • I2. When a natural corpus is dominated by one class, the rare classes can be filled with LLM-generated examples, and the value of those examples is shown by whether a small downstream classifier actually improves.
  • I3. Quality control is applied per contributor rather than per item: reviewing a 10% sample from each person and excluding unreliable people entirely keeps a large crowd dataset clean at low cost.
  • I4. An automatic dialect identifier's output was cross-checked with a small manual sample, which gives a cheap sanity bound on the tool's reliability.
  • I5. Borderline requests such as treating a bone fracture or selling an organ show that harm depends on intent and context more than on topic words, which is why the authors plan multi-label annotation.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Witness-parser agreement in silver data could be scored separately for unlabeled attachment and for the specific relation label, so repair effort targets the genuinely contested layer.
  • I2 (learn): LLM teacher tiers could generate rare constructions such as gapping or unusual voice alternations, keeping them only if a negative-control evaluation shows the parser gains from them.
  • I3 (learn): Silver-data sources and teacher models could be audited on a sampled slice and dropped wholesale when their error rate is too high, instead of filtering sentence by sentence.
  • I4 (tree): When converting between UD dialects or treebanks, a few hundred hand-checked sentences could confirm that automatic conversion statistics are trustworthy.
  • I5 (frames): The speech-act layer could mark directive requests with an explainable risk category derived from the frame (agent, action, patient), allowing multiple labels instead of relying on keywords.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Hamad bin Khalifa UniversityDoha · Qatar141 works · 14,175 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksSocial Sciences · 1,772 worksSafety Research · 543 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 2,908 worksBias, fairness & safety · 517 works

Cite

Cite as Hamdy Mubarak, Abubakr Mohamed and Majd Hawasly. 2025. AraSafe: Benchmarking Safety in Arabic LLMs. Findings of the Association for Computational Linguistics: EMNLP 2025.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.findings-emnlp.529

@inproceedings{mubarak2025arasafe,
  title = {{AraSafe: Benchmarking Safety in Arabic LLMs}},
  author = {Hamdy Mubarak, Abubakr Mohamed and Majd Hawasly},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
  year = {2025},
  doi = {10.18653/v1/2025.findings-emnlp.529},
  url = {https://doi.org/10.18653/v1/2025.findings-emnlp.529}
}

References

30 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdelrahman Abdallah, Mahmoud Kasem, Mahmoud Abdalla, Mohamed Mahmoud, Mohamed Elkasaby, Yasser Elbendary, and Adam Jatowt. 2024. Arabicaqa: A comprehensive dataset for arabic question answering. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 2049–2059, New York, NY, USA. Association for Computing Machinery.
  2. ActiveFence. 2023. Llm safety review: Benchmarks and analysis. Technical report, ActiveFence. find
  3. Emad A. Alghamdi, Reem Masoud, Deema Alnuhait, Afnan Y. Alomairi, Ahmed Ashraf, and Mohamed Zaytoon. 2025. AraTrust: An evaluation of trustworthiness for LLMs in Arabic. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8664–8679, Abu Dhabi, UAE. Association for Computational Linguistics. ↗
  4. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. Arabert: Transformer-based model for arabic language understanding. In LREC 2020 Workshop Language Resources and Evaluation Conference 11–16 May 2020, page 9. ↗
  5. Yasser Ashraf, Yuxia Wang, Bin Gu, Preslav Nakov, and Timothy Baldwin. 2025. Arabic dataset for LLM safeguard evaluation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5529–5546, Albuquerque, New Mexico. Association for Computational Linguistics. M Saiful Bari, Yazeed Alnumay, Norah A. Alzahrani, Nouf M. Alotaibi, Hisham Abdullah Alyahya, Sultan AlRashed, Faisal Abdulrahman Mirza, Shaykhah Z. Alsubaie, Hassan A. Alahmed, Ghadah Alabduljabbar, Raghad Alkhathran, Yousef Almushayqih, Raneem Alnajim, Salman Alsubaihi, Maryam Al Mansour, Saad Amin Hassan, Dr. ↗
  6. Majed Alrubaian, Ali Alammari, Zaki Alawami, Abdulmohsen Al-Thubaity, Ahmed Abdelali, Jeril Kuriakose, Abdalghani Abujabal, Nora Al-Twairesh, Areeb Alowisheq, and Haidar Khan. 2025. ALLam: Large language models for arabic and english. In The Thirteenth International Conference on Learning Representations.
  7. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2318–2335, Bangkok, Thailand. Association for Computational Linguistics.
  8. Ona de Gibert, Naiara Perez, Aitor García-Pablos, and Montse Cuadros. 2018. Hate speech dataset from a white supremacy forum. In Proceedings of the 2nd Workshop on Abusive Language Online (ALW2), pages 11–20, Brussels, Belgium. Association for Computational Linguistics.
  9. Adrian de Wynter, Ishaan Watts, Tua Wongsangaroonsri, Minghui Zhang, Noura Farra, Nektar Ege Altıntoprak, Lena Baur, Samantha Claudet, Pavel Gajdušek, Qilong Gu, et al. 2025. Rtp-lx: Can llms evaluate toxicity in multilingual scenarios? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 27940–27950. find
  10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805. ↗
  11. Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad, Firoj Alam, Enes Altinisik, Ehsannedin Asgari, Yazan Boshmaf, Sabri Boughorbel, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Masoomali Fatehkia, Anastasios Fragkopoulos, Maram Hasanain, Majd Hawasly, Mus’ab Husaini, Soon-Gyo Jung, Ji Kim Lucas, Walid Magdy, Safa Messaoud, Abubakr Mohamed, Tasnim Mohiuddin, Basel Mousi, Hamdy Mubarak, Ahmad Musleh, Zan Naeem, Mourad Ouzzani, Dorde Popovic, Amin Sadeghi, Husrev Taha Sencar, Mohammed Shinoy, Omar Sinan, Yifan Zhang, Ahmed Ali, Yassine El Kheir, Xiaosong Ma, and Chaoyi Ruan. 2025. Fanar: An arabic-centric multimodal generative ai platform. Preprint, arXiv:2501.13944. ↗
  12. Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A. Smith. 2020. RealToxicityPrompts: Evaluating neural toxic degeneration in language models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3356–3369, Online. Association for Computational Linguistics. ↗
  13. Gemma Team. 2024. Gemma. Google. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurelien Rodriguez, Austen Gregerson, Ava Spataru, Baptiste Roziere, Bethany Biron, Binh Tang, Bobbie Chern, Charlotte Caucheteux, Chaya Nayak, Chloe Bi, Chris Marra, Chris McConnell, Christian Keller, Christophe Touret, Chunyang Wu, Corinne Wong, Cristian Canton Ferrer, Cyrus Nikolaidis, Damien Allonsius, Daniel Song, Danielle Pintz, Danny Livshits, Danny Wyatt, David Esiobu, Dhruv Choudhary, Dhruv Mahajan, Diego Garcia-Olano, Diego Perino, Dieuwke Hupkes, Egor Lakomkin, Ehab AlBadawy, Elina Lobanova, Emily Dinan, Eric Michael Smith, Filip Radenovic, Francisco Guzmán, Frank Zhang, Gabriel Synnaeve, Gabrielle Lee, Georgia Lewis Anderson, Govind Thattai, Graeme Nail, Gregoire Mialon, Guan Pang, Guillem Cucurell, Hailey Nguyen, Hannah Korevaar, Hu Xu, Hugo Touvron, Iliyan Zarov, Imanol Arrieta Ibarra, Isabel Kloumann, Ishan Misra, Ivan Evtimov, Jack Zhang, Jade Copet, Jaewon Lee, Jan Geffert, Jana Vranes, Jason Park, Jay Mahadeokar, Jeet Shah, Jelmer van der Linde, Jennifer Billock, Jenny Hong, Jenya Lee, Jeremy Fu, Jianfeng Chi, Jianyu Huang, Jiawen Liu, Jie Wang, Jiecao Yu, Joanna Bitton, Joe Spisak, Jongsoo Park, Joseph Rocca, Joshua Johnstun, Joshua Saxe, Junteng Jia, Kalyan Vasuden Alwala, Karthik Prasad, Kartikeya Upasani, Kate Plawiak, Ke Li, Kenneth Heafield, Kevin Stone, Khalid El-Arini, Krithika Iyer, Kshitiz Malik, Kuenley Chiu, Kunal Bhalla, Kushal Lakhotia, Lauren Rantala-Yeary, Laurens van der Maaten, Lawrence Chen, Liang Tan, Liz Jenkins, Louis Martin, Lovish Madaan, Lubo Malo, Lukas Blecher, Lukas Landzaat, Luke de Oliveira, Madeline Muzzi, Mahesh Pasupuleti, Mannat Singh, Manohar Paluri, Marcin Kardas, Maria Tsimpoukelli, Mathew Oldham, Mathieu Rita, Maya Pavlova, Melanie Kambadur, Mike Lewis, Min Si, Mitesh Kumar Singh, Mona Hassan, Naman Goyal, Narjes Torabi, Nikolay Bashlykov, Nikolay Bogoychev, Niladri Chatterji, Ning Zhang, Olivier Duchenne, Onur Çelebi, Patrick Alrassy, Pengchuan Zhang, Pengwei Li, Petar Vasic, Peter Weng, Prajjwal Bhargava, Pratik Dubal, Praveen Krishnan, Punit Singh Koura, Puxin Xu, Qing He, Qingxiao Dong, Ragavan Srinivasan, Raj Ganapathy, Ramon Calderer, Ricardo Silveira Cabral, Robert Stojnic, Roberta Raileanu, Rohan Maheswari, Rohit Girdhar, Rohit Patel, Romain Sauvestre, Ronnie Polidoro, Roshan Sumbaly, Ross Taylor, Ruan Silva, Rui Hou, Rui Wang, Saghar Hosseini, Sahana Chennabasappa, Sanjay Singh, Sean Bell, Seohyun Sonia Kim, Sergey Edunov, Shaoliang Nie, Sharan Narang, Sharath Raparthy, Sheng Shen, Shengye Wan, Shruti Bhosale, Shun Zhang, Simon Vandenhende, Soumya Batra, Spencer Whitman, Sten Sootla, Stephane Collot, Suchin Gururangan, Sydney Borodinsky, Tamar Herman, Tara Fowler, Tarek Sheasha, Thomas Georgiou, Thomas Scialom, Tobias Speckbacher, Todor Mihaylov, Tong Xiao, Ujjwal Karn, Vedanuj Goswami, Vibhor Gupta, Vignesh Ramanathan, Viktor Kerkez, Vincent Gonguet, Virginie Do, Vish Vogeti, Vítor Albiero, Vladan Petrovic, Weiwei Chu, Wenhan Xiong, Wenyin Fu, Whitney Meers, Xavier Martinet, Xiaodong Wang, Xiaofang Wang, Xiaoqing Ellen Tan, Xide Xia, Xinfeng Xie, Xuchao Jia, Xuewei Wang, Yaelle Goldschlag, Yashesh Gaur, Yasmine Babaei, Yi Wen, Yiwen Song, Yuchen Zhang, Yue Li, Yuning Mao, Zacharie Delpierre Coudert, Zheng Yan, Zhengxing Chen, Zoe Papakipos, Aaditya Singh, Aayushi Srivastava, Abha Jain, Adam Kelsey, Adam Shajnfeld, Adithya Gangidi, Adolfo Victoria, Ahuva Goldstand, Ajay Menon, Ajay Sharma, Alex Boesenberg, Alexei Baevski, Allie Feinstein, Amanda Kallet, Amit Sangani, Amos Teo, Anam Yunus, Andrei Lupu, Andres Alvarado, Andrew Caples, Andrew Gu, Andrew Ho, Andrew Poulton, Andrew Ryan, Ankit Ramchandani, Annie Dong, Annie Franco, Anuj Goyal, Aparajita Saraf, Arkabandhu Chowdhury, Ashley Gabriel, Ashwin Bharambe, Assaf Eisenman, Azadeh Yazdan, Beau James, Ben Maurer, Benjamin Leonhardi, Bernie Huang, Beth Loyd, Beto De Paola, Bhargavi Paranjape, Bing Liu, Bo Wu, Boyu Ni, Braden Hancock, Bram Wasti, Brandon Spence, Brani Stojkovic, Brian Gamido, Britt Montalvo, Carl Parker, Carly Burton, Catalina Mejia, Ce Liu, Changhan Wang, Changkyu Kim, Chao Zhou, Chester Hu, Ching-Hsiang Chu, Chris Cai, Chris Tindal, Christoph Feichtenhofer, Cynthia Gao, Damon Civin, Dana Beaty, Daniel Kreymer, Daniel Li, David Adkins, David Xu, Davide Testuggine, Delia David, Devi Parikh, Diana Liskovich, Didem Foss, Dingkang Wang, Duc Le, Dustin Holland, Edward Dowling, Eissa Jamil, Elaine Montgomery, Eleonora Presani, Emily Hahn, Emily Wood, Eric-Tuan Le, Erik Brinkman, Esteban Arcaute, Evan Dunbar, Evan Smothers, Fei Sun, Felix Kreuk, Feng Tian, Filippos Kokkinos, Firat Ozgenel, Francesco Caggioni, Frank Kanayet, Frank Seide, Gabriela Medina Florez, Gabriella Schwarz, Gada Badeer, Georgia Swee, Gil Halpern, Grant Herman, Grigory Sizov, Guangyi, Zhang, Guna Lakshminarayanan, Hakan Inan, Hamid Shojanazeri, Han Zou, Hannah Wang, Hanwen Zha, Haroun Habeeb, Harrison Rudolph, Helen Suk, Henry Aspegren, Hunter Goldman, Hongyuan Zhan, Ibrahim Damlaj, Igor Molybog, Igor Tufanov, Ilias Leontiadis, Irina-Elena Veliche, Itai Gat, Jake Weissman, James Geboski, James Kohli, Janice Lam, Japhet Asher, Jean-Baptiste Gaya, Jeff Marcus, Jeff Tang, Jennifer Chan, Jenny Zhen, Jeremy Reizenstein, Jeremy Teboul, Jessica Zhong, Jian Jin, Jingyi Yang, Joe Cummings, Jon Carvill, Jon Shepard, Jonathan Mc-Phie, Jonathan Torres, Josh Ginsburg, Junjie Wang, Kai Wu, Kam Hou U, Karan Saxena, Kartikay Khandelwal, Katayoun Zand, Kathy Matosich, Kaushik Veeraraghavan, Kelly Michelena, Keqian Li, Kiran Jagadeesh, Kun Huang, Kunal Chawla, Kyle Huang, Lailin Chen, Lakshya Garg, Lavender A, Leandro Silva, Lee Bell, Lei Zhang, Liangpeng Guo, Licheng Yu, Liron Moshkovich, Luca Wehrstedt, Madian Khabsa, Manav Avalani, Manish Bhatt, Martynas Mankus, Matan Hasson, Matthew Lennie, Matthias Reso, Maxim Groshev, Maxim Naumov, Maya Lathi, Meghan Keneally, Miao Liu, Michael L. Seltzer, Michal Valko, Michelle Restrepo, Mihir Patel, Mik Vyatskov, Mikayel Samvelyan, Mike Clark, Mike Macey, Mike Wang, Miquel Jubert Hermoso, Mo Metanat, Mohammad Rastegari, Munish Bansal, Nandhini Santhanam, Natascha Parks, Natasha White, Navyata Bawa, Nayan Singhal, Nick Egebo, Nicolas Usunier, Nikhil Mehta, Nikolay Pavlovich Laptev, Ning Dong, Norman Cheng, Oleg Chernoguz, Olivia Hart, Omkar Salpekar, Ozlem Kalinli, Parkin Kent, Parth Parekh, Paul Saab, Pavan Balaji, Pedro Rittner, Philip Bontrager, Pierre Roux, Piotr Dollar, Polina Zvyagina, Prashant Ratanchandani, Pritish Yuvraj, Qian Liang, Rachad Alao, Rachel Rodriguez, Rafi Ayub, Raghotham Murthy, Raghu Nayani, Rahul Mitra, Rangaprabhu Parthasarathy, Raymond Li, Rebekkah Hogan, Robin Battey, Rocky Wang, Russ Howes, Ruty Rinott, Sachin Mehta, Sachin Siby, Sai Jayesh Bondu, Samyak Datta, Sara Chugh, Sara Hunt, Sargun Dhillon, Sasha Sidorov, Satadru Pan, Saurabh Mahajan, Saurabh Verma, Seiji Yamamoto, Sharadh Ramaswamy, Shaun Lindsay, Shaun Lindsay, Sheng Feng, Shenghao Lin, Shengxin Cindy Zha, Shishir Patil, Shiva Shankar, Shuqiang Zhang, Shuqiang Zhang, Sinong Wang, Sneha Agarwal, Soji Sajuyigbe, Soumith Chintala, Stephanie Max, Stephen Chen, Steve Kehoe, Steve Satterfield, Sudarshan Govindaprasad, Sumit Gupta, Summer Deng, Sungmin Cho, Sunny Virk, Suraj Subramanian, Sy Choudhury, Sydney Goldman, Tal Remez, Tamar Glaser, Tamara Best, Thilo Koehler, Thomas Robinson, Tianhe Li, Tianjun Zhang, Tim Matthews, Timothy Chou, Tzook Shaked, Varun Vontimitta, Victoria Ajayi, Victoria Montanez, Vijai Mohan, Vinay Satish Kumar, Vishal Mangla, Vlad Ionescu, Vlad Poenaru, Vlad Tiberiu Mihailescu, Vladimir Ivanov, Wei Li, Wenchen Wang, Wenwen Jiang, Wes Bouaziz, Will Constable, Xiaocheng Tang, Xiaojian Wu, Xiaolan Wang, Xilun Wu, Xinbo Gao, Yaniv Kleinman, Yanjun Chen, Ye Hu, Ye Jia, Ye Qi, Yenda Li, Yilin Zhang, Ying Zhang, Yossi Adi, Youngjin Nam, Yu, Wang, Yu Zhao, Yuchen Hao, Yundi Qian, Yunlu Li, Yuzi He, Zach Rait, Zachary DeVito, Zef Rosnbrick, Zhaoduo Wen, Zhenyu Yang, Zhiwei Zhao, and Zhiyu Ma. 2024. The llama 3 herd of models. Preprint, arXiv:2407.21783. ↗
  14. Laura Hanu and Unitary team. 2020. Detoxify. Github. https://github.com/unitaryai/detoxify. ↗
  15. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3309–3326, Dublin, Ireland. Association for Computational Linguistics.
  16. Sabit Hassan, Hamdy Mubarak, Ahmed Abdelali, and Kareem Darwish. 2021. ASAD: Arabic social media analytics and unDerstanding. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 113–118, Online. Association for Computational Linguistics.
  17. Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, et al. 2023. Llama guard: Llm-based input-output safeguard for human-ai conversations. arXiv preprint arXiv:2312.06674. ↗
  18. Julia Jaremko, Dagmar Gromann, and Michael Wiegand. 2025. Revisiting implicitly abusive language detection: Evaluating LLMs in zero-shot and few-shot settings. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3879– 3898, Abu Dhabi, UAE. Association for Computational Linguistics. find
  19. Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The hateful memes challenge: Detecting hate speech in multimodal memes. Advances in neural information processing systems, 33:2611–2624. ↗
  20. Priyanshu Kumar, Devansh Jain, Akhila Yerukola, Liwei Jiang, Himanshu Beniwal, Thomas Hartvigsen, and Maarten Sap. 2025. Polyguard: A multilingual safety moderation tool for 17 languages. arXiv preprint arXiv:2504.04377. ↗
  21. Juhao Liang, Zhenyang Cai, Jianqing Zhu, Huang Huang, Kewei Zong, Bang An, Mosen Alharthi, Juncai He, Lian Zhang, Haizhou Li, Benyou Wang, and Jinchao Xu. 2024. Alignment at pre-training! towards native alignment for arabic LLMs. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
  22. 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. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4694–4702, Singapore. Association for Computational Linguistics.
  23. Hamdy Mubarak, Hend Al-Khalifa, and Abdulmohsen Al-Thubaity. 2022. Overview of OSACT5 shared task on Arabic offensive language and hate speech detection. In Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur‘an QA and Fine-Grained Hate Speech Detection, pages 162–166, Marseille, France. European Language Resources Association.
  24. Hamdy Mubarak, Kareem Darwish, and Walid Magdy. 2017. Abusive language detection on Arabic social media. In Proceedings of the First Workshop on Abusive Language Online, pages 52–56, Vancouver, BC, Canada. Association for Computational Linguistics.
  25. Hamdy Mubarak, Kareem Darwish, Walid Magdy, Tamer Elsayed, and Hend Al-Khalifa. 2020. Overview of OSACT4 Arabic offensive language detection shared task. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 48–52, Marseille, France. European Language Resource Association.
  26. Hala Mulki, Hatem Haddad, Chedi Bechikh Ali, and Halima Alshabani. 2019. L-HSAB: A Levantine Twitter dataset for hate speech and abusive language. In Proceedings of the Third Workshop on Abusive Language Online, pages 111–118, Florence, Italy. Association for Computational Linguistics.
  27. Haitham Seelawi, Ibraheem Tuffaha, Mahmoud Gzawi, Wael Farhan, Bashar Talafha, Riham Badawi, Zyad Sober, Oday Al-Dweik, Abed Alhakim Freihat, and Hussein Al-Natsheh. 2021. ALUE: Arabic language understanding evaluation. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 173–184, Kyiv, Ukraine (Virtual). Association for Computational Linguistics.
  28. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, Lalit Pradhan, Zain Muhammad Mujahid, Massa Baali, Alham Fikri Aji, Zhengzhong Liu, Andy Hock, Andrew Feldman, Jonathan Lee, Andrew Jackson, Preslav Nakov, Timothy Baldwin, and Eric Xing. 2023. Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models. Preprint, arXiv:2308.16149. ↗
  29. Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han, Shom Lin, Zhenxuan Zhang, Angela Zhao, Preslav Nakov, and Timothy Baldwin. 2024. A Chinese dataset for evaluating the safeguards in large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3106– 3119, Bangkok, Thailand. Association for Computational Linguistics. find
  30. Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, and Minlie Huang. 2024. SafetyBench: Evaluating the safety of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15537–15553, Bangkok, Thailand. Association for Computational Linguistics. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/mubarak-2025-arasafe-benchmarking-safety-arabic-llms/