Ali Shahroor

CritiSense: Critical Digital Literacy and Resilience Against Misinformation

F. Alam, F. Ahmad, A. E. Shahroor, M. B. Kmainasi, E. Sartori, G. Da San Martino, A. Hasnat, R. Ali

ACL Demo 2026 Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, System Demonstrations, pages 481-492.

A multilingual media-literacy app for prebunking misinformation through short interactive challenges, instant feedback, and modular lessons. The usability study reports 93 users, 83.9% overall satisfaction, 90.1% ease-of-use ratings, and 500+ active users over six months.

@inproceedings{alam-etal-2026-critisense,
  title     = {{C}riti{S}ense: Critical Digital Literacy and Resilience Against Misinformation},
  author    = {Alam, Firoj and Ahmad, Fatema and Shahroor, Ali Ezzat and Kmainasi, Mohamed Bayan and Sartori, Elisa and Da San Martino, Giovanni and Hasnat, Abul and Ali, Raian},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year      = {2026},
  pages     = {481--492},
  doi       = {10.18653/v1/2026.acl-demo.48},
  url       = {https://aclanthology.org/2026.acl-demo.48/}
}

MemeLens: Multilingual Multitask VLMs for Memes

A. E. Shahroor, M. B. Kmainasi, A. Hasnat, D. Dimitrov, G. Da San Martino, P. Nakov, F. Alam

arXiv 2026 1 citation arXiv:2601.12539.

A unified multilingual, multitask VLM for meme understanding, built from 38 public meme datasets mapped into a shared taxonomy across 20 tasks and 9 languages.

Can Thinking Models Think to Detect Hateful Memes?

M. B. Kmainasi, M. Kutlu, A. E. Shahroor, A. Hasnat, F. Alam

WWW Companion 2026 Companion Proceedings of the ACM Web Conference 2026, pages 935-944.

An empirical study of thinking-based multimodal LLMs for hateful meme analysis, showing how reinforcement learning and rationale supervision improve classification and explanation quality.

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

M. B. Kmainasi, M. Kutlu, A. E. Shahroor, A. Hasnat, F. Alam

arXiv 2026 arXiv:2606.15307.

A reinforcement-learning approach for explainable hateful and propagandistic meme detection, using chain-of-thought supervision, task-specific rewards, and GRPO across English and Arabic benchmarks.

PropXplain: Can LLMs Enable Explainable Propaganda Detection?

M. Hasanain, M. A. Hasan, M. B. Kmainasi, E. Sartori, A. E. Shahroor, G. Da San Martino, F. Alam

EMNLP 2025 Findings 13 citations Explanation-enhanced propaganda detection in Arabic and English.

A multilingual Arabic-English dataset and model setup for propaganda detection with explanations, designed to make classification decisions more transparent and useful for media-literacy contexts.

@inproceedings{hasanain2025propxplain,
  title     = {PropXplain: Can LLMs Enable Explainable Propaganda Detection?},
  author    = {Hasanain, Maram and Hasan, Md. Arid and Kmainasi, Mohamed Bayan and Sartori, Elisa and Shahroor, Ali Ezzat and Da San Martino, Giovanni and Alam, Firoj},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
  year      = {2025},
  url       = {https://aclanthology.org/2025.findings-emnlp.1296/}
}

MemeIntel: Explainable Detection of Propagandistic and Hateful Memes

M. B. Kmainasi, A. Hasnat, M. A. Hasan, A. E. Shahroor, F. Alam

EMNLP 2025 12 citations Explainable multimodal detection with the MemeXplain dataset.

An explanation-enhanced approach for Arabic propagandistic memes and English hateful memes, pairing label detection with natural-language rationales.

@inproceedings{kmainasi2025memeintel,
  title     = {MemeIntel: Explainable Detection of Propagandistic and Hateful Memes},
  author    = {Kmainasi, Mohamed Bayan and Hasnat, Abul and Hasan, Md. Arid and Shahroor, Ali Ezzat and Alam, Firoj},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year      = {2025},
  url       = {https://aclanthology.org/2025.emnlp-main.1539/}
}

Can Large Language Models Predict the Outcome of Judicial Decisions?

M. B. Kmainasi, A. E. Shahroor, A. Al-Ghraibah

arXiv 2025 6 citations arXiv:2501.09768.

An Arabic legal judgment prediction study using Saudi commercial court judgments, benchmarking open-source LLMs under zero-shot, one-shot, and LoRA fine-tuning settings.

EverydayMMQA: A Multilingual and Multimodal Framework for Culturally Grounded Spoken Visual QA

F. Alam, A. E. Shahroor, M. A. Hasan, Z. S. Ali, H. H. Bhatti, M. B. Kmainasi, et al.

arXiv 2025 1 citation arXiv:2510.06371.

A culturally grounded spoken visual QA framework and resource, also released as OASIS, covering image, text, speech, and speech+image settings for Arabic and English contexts.

Native vs Non-Native Language Prompting: A Comparative Analysis

M. B. Kmainasi, R. Khan, A. E. Shahroor, B. Bendou, M. Hasanain, F. Alam

WISE 2024 20 citations International Conference on Web Information Systems Engineering, pages 406-420.

A study of native, non-native, and mixed-language prompting strategies across 11 Arabic NLP tasks and 198 experiments, showing how prompt language affects LLM performance.

@inproceedings{kmainasi2024native,
  title     = {Native vs Non-Native Language Prompting: A Comparative Analysis},
  author    = {Kmainasi, Mohamed Bayan and Khan, Rakif and Shahroor, Ali Ezzat and Bendou, Boushra and Hasanain, Maram and Alam, Firoj},
  booktitle = {Web Information Systems Engineering -- WISE 2024},
  pages     = {406--420},
  year      = {2024},
  url       = {https://doi.org/10.1007/978-981-96-0576-7_30}
}

LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content

M. B. Kmainasi, A. E. Shahroor, M. Hasanain, S. R. Laskar, N. Hassan, F. Alam

NAACL 2025 Findings 17 citations Findings of ACL: NAACL 2025, pages 5627-5649.

A specialized multilingual LLM for analyzing news and social media content across Arabic, English, and Hindi, covering 18 tasks and 52 datasets.

@inproceedings{kmainasi2025llamalens,
  title     = {LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content},
  author    = {Kmainasi, Mohamed Bayan and Shahroor, Ali Ezzat and Hasanain, Maram and Laskar, Sahinur Rahman and Hassan, Naeemul and Alam, Firoj},
  booktitle = {Findings of the Association for Computational Linguistics: NAACL 2025},
  year      = {2025},
  url       = {https://aclanthology.org/2025.findings-naacl.313/}
}