Firoj Alam | LLMs, NLP, Speech, and Disinformation Research

Short Bio: I am a Senior Scientist at the Qatar Computing Research Institute. I received my PhD in Computer Science from the University of Trento, under the supervision of Prof. Giuseppe Riccardi, where I also earned my master’s degree. I completed my undergraduate studies at BRAC University. I have authored numerous peer-reviewed publications and served as LPI and PI on several local, international, and EU-funded research projects. Beyond my research, I actively organize workshops and shared tasks, and mentor students and junior researchers. My work focuses on advancing AI technologies for low-resource and underrepresented languages.

Research Interests:

AI / Deep Learning / Machine Learning: Large Language Models, Multitask and Multimodal Learning, Multilingual Models, Multilingual and Multimodal Representation Learning
Applied Contexts: Social Media Content Analysis, Human–LLM Interaction

Find me here: LinkedIn | Google-Scholar | Researchgate | Github | Bangla NLP

Affliated member: ACL, ACM, IEEE, AAAI, ISCA

news

Sep 18, 2026	Papers to be presented at EMNLP 2026!
Jul 09, 2026	Organizing MMCultureQA at SemEval 2027
Jun 09, 2026	Papers Accepted at Interspeech 2026!
May 28, 2026	Papers Accepted at ACL 2026!
May 14, 2026	Beyond MCQ: Open-Ended Arabic LLM Evaluation Presented at LREC 2026

latest posts

Aug 09, 2024	ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content
Aug 09, 2024	ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content
May 23, 2024	Can GPT-4 Identify Propaganda?

selected publications

Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti , and 2 more authors

In Findings of the Association for Computational Linguistics: EMNLP 2026 , Oct 2026

Accepted for publication

Bib

@inproceedings{ahmed2026multiturn,
  title = {Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges},
  author = {Sara, Syeda Faiza Ahmed and Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  address = {Budapest, Hungary},
  month = oct,
  note = {Accepted for publication},
  url = {https://arxiv.org/abs/2608.17605},
}

OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA

Firoj Alam, Ali Ezzat Shahroor, Md. Arid Hasan , and 8 more authors

arXiv preprint arXiv:2510.06371, Oct 2025

Bib

@article{alam2025everydaymmqa,
  title = {{OASIS}: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA},
  author = {Alam, Firoj and Shahroor, Ali Ezzat and Hasan, Md. Arid and Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Kmainasi, Mohamed Bayan and Chowdhury, Shammur Absar and Mousi, Basel and Dalvi, Fahim and Durrani, Nadir and Milic-Frayling, Natasa},
  journal = {arXiv preprint arXiv:2510.06371},
  year = {2025},
}

Advances in AI Systems on Islamic Knowledge Capabilities: A Critical Survey

Gagan Bhatia, Hamdy Mubarak, Majd Hawasly , and 9 more authors

Feb 2026

Bib

@article{Bhatia_2026,
  title = {Advances in AI Systems on Islamic Knowledge Capabilities: A Critical Survey},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Bhatia, Gagan and Mubarak, Hamdy and Hawasly, Majd and Jarrar, Mustafa and Mikros, George and Zaraket, Fadi and Alhirthani, Mahmoud and Al-Khatib, Mutaz and Cochrane, Logan and Darwish, Kareem and Yahiaoui, Rashid and Alam, Firoj},
  url = {http://dx.doi.org/10.36227/techrxiv.177155997.77147487/v1},
  doi = {10.36227/techrxiv.177155997.77147487/v1},
  year = {2026},
  month = feb,
}

MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs

Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi , and 2 more authors

In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing , Oct 2026

Bib

@inproceedings{ali2026menaspeechbank,
  title = {{MENASpeechBank}: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for {AudioLLMs}},
  author = {Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Nandi, Rabindra Nath and Chowdhury, Shammur Absar and Alam, Firoj},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  address = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  month = oct,
  year = {2026},
  url = {https://arxiv.org/abs/2602.07036},
}

From RAG to Agentic RAG for Faithful Islamic Question Answering

Gagan Bhatia, Hamdy Mubarak, Mustafa Jarrar , and 8 more authors

In Findings of the Association for Computational Linguistics: ACL 2026 , Jul 2026

PropXplain: Can LLMs Enable Explainable Propaganda Detection?

Maram Hasanain, Md Arid Hasan, Mohamed Bayan Kmainasi , and 4 more authors

In Findings of the Association for Computational Linguistics: EMNLP 2025 , Nov 2025

Bib

@inproceedings{hasanain-etal-2025-propxplain,
  title = {{P}rop{X}plain: Can {LLM}s 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},
  editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
  month = nov,
  year = {2025},
  address = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.findings-emnlp.1296/},
  doi = {10.18653/v1/2025.findings-emnlp.1296},
  pages = {23855--23863},
  isbn = {979-8-89176-335-7},
}

MemeIntel: Explainable Detection of Propagandistic and Hateful Memes

Mohamed Bayan Kmainasi, Abul Hasnat, Md Arid Hasan , and 2 more authors

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , Nov 2025

Bib

@inproceedings{kmainasi-etal-2025-memeintel,
  title = {{M}eme{I}ntel: 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},
  editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  month = nov,
  year = {2025},
  address = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.emnlp-main.1539/},
  doi = {10.18653/v1/2025.emnlp-main.1539},
  pages = {30251--30267},
  isbn = {979-8-89176-332-6},
}

NativQA: Multilingual Culturally-Aligned Natural Query for LLMs

Md. Arid Hasan, Maram Hasanain, Fatema Ahmad , and 6 more authors

In Findings of the Association for Computational Linguistics: ACL 2025 , Jul 2025
LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content

Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Maram Hasanain , and 3 more authors

In Findings of the Association for Computational Linguistics: NAACL 2025 , Apr 2025

Abs Bib

Large Language Models (LLMs) have demonstrated remarkable success as general-purpose task solvers across various fields. However, their capabilities remain limited when addressing domain-specific problems, particularly in downstream NLP tasks. Research has shown that models fine-tuned on instruction-based downstream NLP datasets outperform those that are not fine-tuned. While most efforts in this area have primarily focused on resource-rich languages like English and broad domains, little attention has been given to multilingual settings and specific domains. To address this gap, this study focuses on developing a specialized LLM, LlamaLens, for analyzing news and social media content in a multilingual context. To the best of our knowledge, this is the first attempt to tackle both domain specificity and multilinguality, with a particular focus on news and social media. Our experimental setup includes 18 tasks, represented by 52 datasets covering Arabic, English, and Hindi. We demonstrate that LlamaLens outperforms the current state-of-the-art (SOTA) on 23 testing sets, and achieves comparable performance on 8 sets. We make the models and resources publicly available for the research community (https://huggingface.co/QCRI).
@inproceedings{kmainasi-etal-2025-llamalens, title = {{L}lama{L}ens: 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}, editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu}, booktitle = {Findings of the Association for Computational Linguistics: NAACL 2025}, month = apr, year = {2025}, address = {Albuquerque, New Mexico}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2025.findings-naacl.313/}, pages = {5627--5649}, isbn = {979-8-89176-195-7}, }

AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs

Basel Mousi, Nadir Durrani, Fatema Ahmad , and 6 more authors

In Proceedings of the 31st International Conference on Computational Linguistics , Jan 2025

Bib

@inproceedings{mousi-etal-2025-aradice,
  title = {{A}ra{D}i{CE}: Benchmarks for Dialectal and Cultural Capabilities in {LLM}s},
  author = {Mousi, Basel and Durrani, Nadir and Ahmad, Fatema and Hasan, Md. Arid and Hasanain, Maram and Kabbani, Tameem and Dalvi, Fahim and Chowdhury, Shammur Absar and Alam, Firoj},
  editor = {Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  month = jan,
  year = {2025},
  address = {Abu Dhabi, UAE},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.coling-main.283/},
  pages = {4186--4218},
}

LAraBench: Benchmarking Arabic AI with Large Language Models

Ahmed Abdelali, Hamdy Mubarak, Shammur Chowdhury , and 14 more authors

In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , Mar 2024

Abs Bib

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particular languages and tasks. LAraBench addresses this gap for Arabic Natural Language Processing (NLP) and Speech Processing tasks, including sequence tagging and content classification across different domains. We utilized models such as GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM, employing zero and few-shot learning techniques to tackle 33 distinct tasks across 61 publicly available datasets. This involved 98 experimental setups, encompassing ~296K data points, ~46 hours of speech, and 30 sentences for Text-to-Speech (TTS). This effort resulted in 330+ sets of experiments. Our analysis focused on measuring the performance gap between SOTA models and LLMs. The overarching trend observed was that SOTA models generally outperformed LLMs in zero-shot learning, with a few exceptions. Notably, larger computational models with few-shot learning techniques managed to reduce these performance gaps. Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.
@inproceedings{abdelali-etal-2024-larabench, address = {St. Julian{'}s, Malta}, author = {Abdelali, Ahmed and Mubarak, Hamdy and Chowdhury, Shammur and Hasanain, Maram and Mousi, Basel and Boughorbel, Sabri and Abdaljalil, Samir and El Kheir, Yassine and Izham, Daniel and Dalvi, Fahim and Hawasly, Majd and Nazar, Nizi and Elshahawy, Youssef and Ali, Ahmed and Durrani, Nadir and Milic-Frayling, Natasa and Alam, Firoj}, booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)}, date-modified = {2024-08-03 11:44:50 +0300}, editor = {Graham, Yvette and Purver, Matthew}, month = mar, pages = {487--520}, publisher = {Association for Computational Linguistics}, title = {{LA}ra{B}ench: Benchmarking {A}rabic {AI} with Large Language Models}, year = {2024}, url = {https://aclanthology.org/2024.eacl-long.30}, }
LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking

Fahim Dalvi, Maram Hasanain, Sabri Boughorbel , and 10 more authors

In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations , Mar 2024

Abs Bib

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online (https://youtu.be/9cC2m_abk3A).
@inproceedings{dalvi-etal-2024-llmebench, address = {St. Julians, Malta}, author = {Dalvi, Fahim and Hasanain, Maram and Boughorbel, Sabri and Mousi, Basel and Abdaljalil, Samir and Nazar, Nizi and Abdelali, Ahmed and Chowdhury, Shammur Absar and Mubarak, Hamdy and Ali, Ahmed and Hawasly, Majd and Durrani, Nadir and Alam, Firoj}, booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations}, date-modified = {2024-08-03 11:44:50 +0300}, editor = {Aletras, Nikolaos and De Clercq, Orphee}, month = mar, pages = {214--222}, publisher = {Association for Computational Linguistics}, title = {{LLM}e{B}ench: A Flexible Framework for Accelerating {LLM}s Benchmarking}, year = {2024}, url = {https://aclanthology.org/2024.eacl-demo.23}, }
Large Language Models for Propaganda Span Annotation

Maram Hasanain, Fatema Ahmad, and Firoj Alam

In Findings of the Association for Computational Linguistics: EMNLP 2024 , Nov 2024

Abs Bib

The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are essential for more informed content consumption. Automatic systems targeting the task over lower resourced languages are limited, usually obstructed by lack of large scale training datasets. Our study investigates whether Large Language Models (LLMs), such as GPT-4, can effectively extract propagandistic spans. We further study the potential of employing the model to collect more cost-effective annotations. Finally, we examine the effectiveness of labels provided by GPT-4 in training smaller language models for the task. The experiments are performed over a large-scale in-house manually annotated dataset. The results suggest that providing more annotation context to GPT-4 within prompts improves its performance compared to human annotators. Moreover, when serving as an expert annotator (consolidator), the model provides labels that have higher agreement with expert annotators, and lead to specialized models that achieve state-of-the-art over an unseen Arabic testing set. Finally, our work is the first to show the potential of utilizing LLMs to develop annotated datasets for propagandistic spans detection task prompting it with annotations from human annotators with limited expertise. All scripts and annotations will be shared with the community.
@inproceedings{hasanain-etal-2024-large, title = {Large Language Models for Propaganda Span Annotation}, author = {Hasanain, Maram and Ahmad, Fatema and Alam, Firoj}, editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024}, month = nov, year = {2024}, address = {Miami, Florida, USA}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2024.findings-emnlp.850}, pages = {14522--14532}, }

Discovering Latent Concepts Learned in BERT

Fahim Dalvi, Abdul Rafae Khan, Firoj Alam , and 3 more authors

In International Conference on Learning Representations , Nov 2022

Bib

@inproceedings{dalvi2022discovering,
  author = {Dalvi, Fahim and Khan, Abdul Rafae and Alam, Firoj and Durrani, Nadir and Xu, Jia and Sajjad, Hassan},
  booktitle = {International Conference on Learning Representations},
  title = {Discovering Latent Concepts Learned in {BERT}},
  year = {2022},
  url = {https://openreview.net/forum?id=POTMtpYI1xH},
}