Elamur Research⌕
☰
home / papers / 2025 / The AraGenEval Shared Task on Arabic Authorship Style Transfer and AI Generated Text Detection

The AraGenEval Shared Task on Arabic Authorship Style Transfer and AI Generated Text Detection

Summary

AraGenEval was a shared task at ArabicNLP 2025 (co-located with EMNLP 2025). It filled a gap: Arabic had no dedicated benchmark for imitating an author's style or for telling human writing from machine writing. The organizers defined three subtasks. The first, Authorship Style Transfer, rewrites a formal Arabic passage in the voice of a chosen author. The second, Authorship Identification, is a multiclass attribution task. The third, ARATECT, separates human from LLM-produced news and literary text. The data includes more than 47,000 paragraphs from 21 classical and modern writers, plus a balanced human/AI corpus. Scoring used BLEU and chrF for generation, macro-F1 for attribution, and accuracy/F1 for detection. Transformers dominated every subtask. The strongest systems used instruction-style prompting for rewriting, ensembles for attribution, and a blend of multilingual and Arabic-specific encoders for detection. The work matters because detectors and models built for English transfer poorly to Arabic, which has complex morphology, diglossia and diacritics. Arabic stylistics and trustworthy NLP needed a shared Arabic testbed.

Key points

  • Participation: 72 registered teams (115 people) from 16 countries made 37 unique leaderboard submissions.
  • Style transfer: ANLPers won with BLEU 24.58 using prompt engineering on AraT5. Nojoom.AI was close behind at 24.46 BLEU but scored slightly higher on chrF (59.33 vs 59.01). Other entries used mBART, AraT5 fine-tuning and LoRA on Qwen2.5-7B-Instruct.
  • Authorship identification: Sebaweh won with macro-F1 0.8989 (accuracy 0.9242) using an ensemble of four transformers. Second place, at 0.8716, fused the logits of AraBERT and AraELECTRA. The top 11 teams were within about 10% of each other.
  • Even in that tight field, simpler pipelines such as TF-IDF with logistic regression and XLM-R embeddings with a LinearSVC stayed competitive. Fine-tuned ALLaM-7B-Instruct, AraBERT(v2) and CAMeLBERT were also common.
  • AI-text detection: LMSA led with F1 0.8641. The authors list three limitations:
    • The detection training data came from a fixed set of generators.
    • The style data covers only 21 mostly literary authors.
    • BLEU/chrF do not truly measure stylistic fidelity or meaning preservation.

Interesting ideas

  • I1. Scoring generation with two surface metrics showed that BLEU and chrF can disagree on rank. The organizers admit neither metric checks whether meaning survived, so an honest evaluation needs a content-level check alongside n-gram overlap. — For Mova (back): Judge the text → graph → text compressor by reparsing the output and comparing the meaning graphs, with BLEU/chrF kept only as secondary signals.
  • I2. The runner-up in attribution fused logits from two differently pretrained encoders (AraBERT and AraELECTRA). Combining models with different inductive biases gave robustness that neither model had alone. — For Mova (learn): Weight silver-data agreement among witness parsers by their confidence distributions instead of a hard majority vote, preferring witnesses that were trained differently.
  • I3. A plain TF-IDF + logistic regression attribution system landed near transformer systems. A cheap lexical baseline is therefore a useful yardstick for whether heavier structure actually earns its cost. — For Mova (learn): Keep a bag-of-words classifier as a standing negative control in evaluations, so we can show where the tree-and-frames pipeline beats lexical shortcuts and where it does not.
  • I4. The winning style-transfer approach recast the job as a natural-language instruction to a pretrained model rather than a bespoke architecture. This lets prior knowledge be steered by an explicit target attribute. — For Mova (back): Attach explicit register or style attributes to the meaning graph and have generation condition on them, so stylistic choices stay inspectable rather than hidden.
  • I5. The authors warn that detectors trained on outputs from a fixed set of LLMs may fail on newer generators. They recommend testing with unseen models and adversarial samples. — For Mova (learn): When training from LLM teacher tiers, hold out one teacher entirely at evaluation time to check that learned rules generalize beyond the quirks of the teachers seen in training.

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

Fields: Machine translation · Natural language processing

Topics: Machine translation

Cited by

34 papers of our library cite it (of the 140884 whose bibliographies we read); 6 of them have a page here, 28 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.arabicnlp-sharedtasks.1

@inproceedings{abudalfa2025arageneval,
  title = {{The AraGenEval Shared Task on Arabic Authorship Style Transfer and AI Generated Text Detection}},
  author = {Abudalfa, Shadi and Ezzini, Saad and Abdelali, Ahmed and Alami, Hamza and Benlahbib, Abdessamad and Chafik, Salmane and El-Haj, Mo and Mahdaouy, Abdelkader El and Jarrar, Mustafa and Lamsiyah, Salima and Luqman, Hamzah},
  booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
  year = {2025},
  doi = {10.18653/v1/2025.arabicnlp-sharedtasks.1},
  url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.1}
}

References

77 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Fahad J Abdu, Raed Mughaus, Shadi Abudalfa, Moataz Ahmed, and Ahmed Abdelali. 2025. An empirical evaluation of arabic text formality transfer: a comparative study. Language Resources and Evaluation, pages 1–61. find
  2. Opeyemi Aborisade and Mohd Anwar. 2018. Classification for authorship of tweets by comparing logistic regression and naive bayes classifiers. In 2018 IEEE International Conference on Information Reuse and Integration (IRI), pages 269–276. IEEE. find
  3. Shadi I Abudalfa, Fahad J Abdu, and Maad M Alowaifeer. 2024. Arabic text formality modifica-Rank Team Participant F1-Score Accuracy Paper Submitted LMSA kaoutar 0.8641 0.8660 Yes 2 3 4 5 6 7 8 9 -MISSION PTUK-HULAT BUSTED ANLPers -Osint PalNLP deleted_user_25186 7h4m3r tasneemduridi alizain157 omarnj deleted_user_27804 shifali mutazay 0.8065 0.8044 0.7823 0.7701 0.7617 0.7583 0.7522 0.7443 0.7860 0.7860 0.7640 0.7600 0.7860 0.7680 0.7180 0.7060 No Yes Yes Yes Yes No Yes No NLP_wizard nlp_wizard 0.7423 0.7000 Yes Jenin CUET-NLP_ Team_SS306 CIOL Hedi REGLAT Couger AI jenin 0.6845 0.5520 Yes System Used Ensemble of Fanar, AraBERT, XLM-R -Fine-tuned AraModernBERT Fine-tuned XLM-ROBERTa Fine-tuned XLM-ROBERTa Fine-tuned XLM-ROBERTa -mBERT with linguistic features -XLM-R Embeddings + RidgeClassifier Fine-tuned AraBERT sowravnath 0.6722 0.5280 Yes AraBERT with chunking tasnim_meem seifbenayed mariamlabib sabarinathan1 0.6574 0.6541 0.6289 0.6238 0.7040 0.4860 0.6460 0.5320 Yes No Yes No Fine-tuned AraBERTv2 -Morphology-aware AraBERT - 13 14 15 16 *Table 4: Leaderboard for Subtask 3: Arabic AI-Generated Text Detection (ARATECT). The ranking is based on the primary metric, F1-Score.* tion: A review and future research directions. IEEE Access. authorship attribution. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6105–6119. find
  4. Shifali Agrahari, Hemanth Simhadri, Ashutosh Verma, and Ranbir Sanasam. 2025. Osint at arageneval shared task: Fine-tuned modeling for tracking style signatures and ai generation in arabic texts. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  5. Hamed Alshammari and EI-Sayed Ahmed. 2023. Airabic: Arabic dataset for performance evaluation of ai detectors. In 2023 International Conference on Machine Learning and Applications (ICMLA), pages 864–870. IEEE. find
  6. Hamed Alshammari and Khaled Elleithy. 2024. Toward robust arabic ai-generated text detection: Tackling diacritics challenges. Information, 15(7):419. find
  7. Maged S Al-Shaibani and Moataz Ahmed. 2025. The arabic ai fingerprint: Stylometric analysis and detection of large language models text. arXiv preprint arXiv:2505.23276. ↗ our card
  8. Fetoun Mansour AlZahrani and Maha Al-Yahya. 2023. A transformer-based approach to authorship attribution in classical arabic texts. Applied Sciences, 13(12):7255. find
  9. Mohammad AL-Smadi. 2025. Integrityai at genai detection task 2: Detecting machine-generated academic essays in english and arabic using electra and stylometry. arXiv preprint arXiv:2501.05476. ↗
  10. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020a. AraBERT: Transformer-based model for Arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. find our card
  11. HAMER ALHARBI. 2025. Mission at arageneval shared task: Enhanced arabic authority classification. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  12. Fatimah Alqahtani and Mischa Dohler. 2023. Survey of authorship identification tasks on arabic texts. ACM Transactions on Asian and Low-Resource Language Information Processing, 22(4):1–24. find
  13. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020b. Araelectra: Pre-training text discriminators for arabic language understanding. arXiv preprint arXiv:2012.15516. ↗
  14. Fatimah Alqahtani and Helen Yannakoudakis. 2022. Authorship verification for arabic short texts using arabic knowledge-base model (arakb). In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 205–213. find
  15. Andrea Bacciu, Massimo La Morgia, Alessandro Mei, Eugenio Nerio Nemmi, Valerio Neri, Julinda Stefa, and 1 others. 2019. Cross-domain authorship attribution combining instance-based and profile-based features notebook for pan at clef 2019. In CEUR WORKSHOP PROCEEDINGS, volume 2380. CEUR-WS. find
  16. Lama Alqurashi, Serge Sharoff, Janet Watson, and Jacob Blakesley. 2025. Bert-based classical arabic poetry Douglas Bagnall. 2015. Author identification using multi-headed recurrent neural networks. arXiv preprint arXiv:1506.04891. ↗
  17. Liam Dugan, Andrew Zhu, Firoj Alam, Preslav Nakov, Marianna Apidianaki, and Chris Callison-Burch. 2025. Genai content detection task 3: Cross-domain machine generated text detection challenge. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 377–388. find
  18. Leonard Bauersfeld, Angel Romero, Manasi Muglikar, and Davide Scaramuzza. 2023. Cracking double-blind review: authorship attribution with deep learning. Plos one, 18(6):e0287611. find
  19. Tasneem Duridi, Areej Jaber, and Paloma Martínez. 2025. Ptuk-hulat at arageneval shared task: Fine-tuning xlm-roberta for ai-generated arabic news detection. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  20. Imene Bensalem, Imene Boukhalfa, Paolo Rosso, Lahsen Abouenour, Kareem Darwish, and Salim Chikhi. 2015. Overview of the araplagdet pan@ fire2015 shared task on arabic plagiarism detection. In FIRE workshops, pages 111–122. Md. find
  21. Rafiul Biswas, Mabrouka Bessghaier, Firoj Alam, and Wajdi Zaghouani. 2025a. Marsadlab at arageneval shared task: Llm-based approaches to arabic authorship style transfer and identification. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find our card
  22. Mahmoud El-Haj and Rim Koulali. 2013. Kalimat a multipurpose arabic corpus. Culture, 2:1–359. Md. find
  23. Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Firoj Alam, and Wajdi Zaghouani. 2025b. MarsadLab at AraGenEval: Arabic Authorship Style Transfer and AI Generated Text Detection. In Proceedings of the Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. find
  24. Mahmoud El-Haj, Paul Rayson, and Mariam Aboelezz. 2018. Arabic dialect identification in the context of bivalency and code-switching. In Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan., pages 3622–3627. European Language Resources Association. find
  25. Benedikt Boenninghoff, Steffen Hessler, Dorothea Kolossa, and Robert M Nickel. 2019. Explainable authorship verification in social media via attention-based similarity learning. In 2019 IEEE International Conference on Big Data (Big Data), pages 36–45. IEEE. find
  26. Mo El-Haj, Sultan Almujaiwel, Damith Premasiri, Tharindu Ranasinghe, and Ruslan Mitkov. 2024. Dares: Dataset for arabic readability estimation of school materials. In Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context@ LREC-COLING 2024, pages 103– 113. find
  27. Mahmoud El-Haj and Paul Rayson. 2016. Osman—a novel arabic readability metric. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 250–255. find
  28. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901. find
  29. Mo El-Haj and Saad Ezzini. 2024. The multilingual corpus of world’s constitutions (mcwc). In Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation@ LREC-COLING 2024, pages 57–66. find
  30. Kunal Chawla and Diyi Yang. 2020. Semi-supervised formality style transfer using language model discriminator and mutual information maximization. Preprint, arXiv:2010.05090. ↗
  31. Maël Fabien, Esau Villatoro-Tello, Petr Motlicek, and Shantipriya Parida. 2020. Bertaa: Bert fine-tuning for authorship attribution. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 127–137. find
  32. Shammur Absar Chowdhury, Hind Almerekhi, Mucahid Kutlu, Kaan Efe Keles, Fatema Ahmad, Tasnim Mohiuddin, George Mikros, and Firoj Alam. 2024. Genai content detection task 2: Ai vs. human–academic essay authenticity challenge. arXiv preprint arXiv:2412.18274. ↗
  33. Wooyoung Go, Hyoungshick Kim, Alice Oh, and Yongdae Kim. 2025. XDAC: XAI-driven detection and attribution of LLM-generated news comments in Korean. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 22728–22750, Vienna, Austria. Association for Computational Linguistics. find
  34. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. ↗
  35. Hongyu Gong, Suma Bhat, Lingfei Wu, JinJun Xiong, and Wen-mei Hwu. 2019. Reinforcement learning based text style transfer without parallel training corpus. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3168– 3180, Minneapolis, Minnesota. Association for Computational Linguistics. find
  36. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673. find
  37. Nizar Y Habash. 2010. Introduction to Arabic natural language processing. Morgan & Claypool Publishers. find
  38. John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein. 2023. A watermark for large language models. In International Conference on Machine Learning, pages 17061–17084. PMLR. find our card
  39. Mena Hany. 2025. Nlp_wizard at arageneval shared task: Embedding-based classification for ai detection and authorship attribution. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  40. Mariam Labib, Nsrin Ashraf, Mohammed Aldawsari, and Hamada Nayel. 2025. Reglat at arageneval shared task: Morphology-aware arabert for detecting arabic ai-generated text. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  41. Muhammad Helmy, Batool Najeh Balah, Ahmed Mohamed Sallam, and Ammar Sherif. 2025. Sebaweh at arageneval shared task: Berense - bert based ensembler for arabic authorship identification. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  42. Ksenia Lagutina, Nadezhda Lagutina, Elena Boychuk, Inna Vorontsova, Elena Shliakhtina, Olga Belyaeva, Ilya Paramonov, and PG Demidov. 2019. A survey on stylometric text features. In 2019 25th Conference of Open Innovations Association (FRUCT), pages 184–195. IEEE. find
  43. Zhiqiang Hu, Roy Ka-Wei Lee, Charu C. Aggarwal, and Aston Zhang. 2022. Text style transfer: A review and experimental evaluation. 24(1):14–45. find
  44. Salima Lamsiyah, Saad Ezzini, Abdelkader Elmah-daouy, Hamza Alami, Abdessamad Benlahbib, Samir El Amrany, Salmane Chafik, and Hicham Hammouchi. 2025. Shared task on multi-domain detection of ai-generated text (m-daigt). In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing (RANLP). find
  45. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Toward controlled generation of text. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 1587–1596. JMLR.org. find our card
  46. Yuanfan Li, Zhaohan Zhang, Chengzhengxu Li, Chao Shen, and Xiaoming Liu. 2025. Iron sharpens iron: Defending against attacks in machine-generated text detection with adversarial training. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3091–3113, Vienna, Austria. Association for Computational Linguistics. find
  47. Baixiang Huang, Canyu Chen, and Kai Shu. 2024. Can large language models identify authorship? In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 445–460, Miami, Florida, USA. Association for Computational Linguistics. find
  48. Baixiang Huang, Canyu Chen, and Kai Shu. 2025. Authorship attribution in the era of llms: Problems, methodologies, and challenges. ACM SIGKDD Explorations Newsletter, 26(2):21–43. find
  49. Dominik Macko, Jakub Kopál, Robert Moro, and Ivan Srba. 2025. MultiSocial: Multilingual benchmark of machine-generated text detection of social-media texts. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 727–752, Vienna, Austria. Association for Computational Linguistics. find
  50. Javier Huertas-Tato, Alvaro Huertas-Garcia, Alejandro Martin, and David Camacho. 2022. Part: Pre-trained authorship representation transformer. arXiv preprint arXiv:2209.15373. ↗
  51. Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch, and Douglas Eck. 2020. Automatic detection of generated text is easiest when humans are fooled. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1808–1822, Online. Association for Computational Linguistics. find our card
  52. Sanad Malaysha, Mo El-Haj, Saad Ezzini, Mohammed Khalilia, Mustafa Jarrar, Sultan Almujaiwel, Ismail Berrada, and Houda Bouamor. 2024. Arafinnlp 2024: The first arabic financial nlp shared task. arXiv preprint arXiv:2407.09818. ↗
  53. Huthayfa Malhis, Mohammad Tami, and Huthaifa I. Ashqar. 2025. Jenin at arageneval shared task: Parameter-efficient fine-tuning and layer-wise analysis of arabic llms for authorship style transfer and classification. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find our card
  54. Hafsa KARA ACHIRA, Mourad Bouache, and Mourad Dahmane. 2025. Nojoom.ai at AraGenEval shared task: Advancing authorship style transfer for arabic text. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  55. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. Preprint, arXiv:1609.07843. ↗ our card
  56. Amr Sabaa and Mohamed Sabaa. 2025. Amr&mohamedsabaa at AraGenEval shared task: Arabic authorship identification using term frequency – inverse document frequency features with supervised machine learning. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  57. Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D Manning, and Chelsea Finn. 2023. Detectgpt: Zero-shot machine-generated text detection using probability curvature. In International conference on machine learning, pages 24950–24962. PMLR. find our card
  58. Chakaveh Saedi and Mark Dras. 2021. Siamese networks for large-scale author identification. Computer Speech & Language, 70:101241. find
  59. Frederick Mosteller and David L Wallace. 1963. Inference in an authorship problem: A comparative study of discrimination methods applied to the authorship of the disputed federalist papers. Journal of the American Statistical Association, 58(302):275–309. find
  60. Eman Samir, Mahmoud Rady, Maria Bassem, Mariam Hossam, Amin Mohamed, Nisreen Hisham, and Sara Gaballa. 2025. Athership at arageneval shared task: Identifying arabic authorship with a dual-model logit fusion. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  61. Raed Mughaus, Shadi Abudalfa, Hamzah Luqman, Fahad Abdu, Mohammed AlAli, Nawaf Al-Dowayan, and Ahmed Abdelali. 2025. Ma’aks: manually-curated parallel dataset for arabic text sentiment swap. Language Resources and Evaluation. find
  62. Lujia Shen, Xuhong Zhang, Shouling Ji, Yuwen Pu, Chunpeng Ge, Xing Yang, and Yanghe Feng. 2023. Textdefense: Adversarial text detection based on word importance entropy. arXiv preprint arXiv:2302.05892. ↗
  63. Omer Nacar, Serry Sibaee, Mahmoud Reda, Adel Al-Habashi, Yasser Ammar, and Wadii Boulila. 2025. Anlpers at arageneval shared task: Descriptive author tokens for transparent arabic authorship style transfer. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find our card
  64. Prasha Shrestha, Sebastian Sierra, Fabio González, Manuel Montes, Paolo Rosso, and Thamar Solorio. 2017. Convolutional neural networks for authorship attribution of short texts. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 669–674, Valencia, Spain. Association for Computational Linguistics. find
  65. Sowrav Nath, Shadman Saleh, Kawsar Ahmed, and Mohammed Moshiul Hoque. 2025. Cuet-nlp_team_ss306 at arageneval shared task: A transformer-based framework for detecting ai-generated arabic text. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  66. Zhixiong Su, Yichen Wang, Herun Wan, Zhaohan Zhang, and Minnan Luo. 2025. HACo-det: A study towards fine-grained machine-generated text detection under human-AI coauthoring. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 22015–22036, Vienna, Austria. Association for Computational Linguistics. find
  67. Lei Pan, Yunshi Lan, Yang Li, and Weining Qian. 2024. Unsupervised text style transfer via llms and attention masking with multi-way interactions. Preprint, arXiv:2402.13647. ↗
  68. Chen Qian, Tianchang He, and Rao Zhang. 2017. Deep learning based authorship identification. Report, Stanford University, pages 1–9. find
  69. Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohammed Afzal, Tarek Mahmoud, Giovanni Puccetti, and Thomas Arnold. 2024a. SemEval-2024 task 8: Multidomain, multimodel and multilingual machine-generated text detection. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 2057–2079, Mexico City, Mexico. Association for Computational Linguistics. find
  70. Rafael A Rivera-Soto, Olivia Elizabeth Miano, Juanita Ordonez, Barry Y Chen, Aleem Khan, Marcus Bishop, and Nicholas Andrews. 2021. Learning universal authorship representations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 913–919. find
  71. Paolo Rosso. 2017. Author profiling at PAN: from age and gender identification to language variety identification (invited talk). In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), page 46, Valencia, Spain. Association for Computational Linguistics. find
  72. Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Toru Sasaki, Thomas Arnold, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, and Preslav Nakov. 2024b. M4: Multi-generator, multi-domain, and multi-lingual black-box machine-generated text detection. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages Sebastian Ruder, Parsa Ghaffari, and John G Breslin. 2016. Character-level and multi-channel convolutional neural networks for large-scale authorship attribution. arXiv preprint arXiv:1609.06686. 1369–1407, St. Julian’s, Malta. Association for Computational Linguistics. ↗
  73. Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan, Lidia Sam Chao, and Derek Fai Wong. 2025. A survey on llm-generated text detection: Necessity, methods, and future directions. Computational Linguistics, 51(1):275–338. find our card
  74. Ali Zain, Sareem Farooqui, and Muhammad Rafi. 2025. Busted at arageneval shared task: A comparative study of transformer-based models for arabic ai-generated text detection. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find our card
  75. Xuandong Zhao, Yu-Xiang Wang, and Lei Li. 2023. Protecting language generation models via invisible watermarking. In International Conference on Machine Learning, pages 42187–42199. PMLR. find
  76. Kaoutar Zita, Attia Nehar, Abdelkader Khelil, Slimane Bellaouar, and Hadda Cherroun. 2025. Lmsa at arageneval shared task: Ensemble-based detection of ai-generated arabic text using multilingual and arabic-specific models. In Proceedings of the third Arabic Natural Language Processing Conference, Suzhou, China. Association for Computational Linguistics (ACL). find
  77. Nadhem Zmandar, Mo El-Haj, and Paul Rayson. 2023. FinAraT5: A text to text model for financial Arabic text understanding and generation. In Proceedings of the 4th Conference on Language, Data and Knowledge, pages 262–273, Vienna, Austria. NOVA CLUNL, Portugal. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/abudalfa-2025-arageneval-shared-task-arabic-authorship/