🧑‍🔬 Imran Razzak

🏛️ Affiliations

🎓UNSW SydneySydney · Australia2020–2026 · 144 papersEmployment 2022–2025 · Associate Professor in Human-Centered Machine Learning, Computer Science and EngineeringEmployment since 2025 · Adjuct Associate Professor, Computer Science and Engineeringcurrent🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates2024–2026 · 107 papersEmployment since 2025 · Associate Professor, School of Digital Public Healthcurrent🔬Inception Institute of Artificial IntelligenceAbu Dhabi · United Arab Emirates2026 · 1 papercurrent🎓Deakin UniversityBurwood · Australia2019–2023 · 98 papersEducation 2019–2020 · Graduate Certificate of Higher Education (Learning and Teaching)Employment 2019–2022 · Senior Lecturer in Computer Science, School of Information Technology🎓King Saud bin Abdulaziz University for Health SciencesRiyadh · Saudi Arabia2013–2019 · 37 papers🎓University of Technology SydneySydney · Australia2017–2024 · 24 papersEducation · Doctorate in Analytics, School of Computer ScienceEmployment 2017–2019 · School of Computer Science🎓International Islamic University, IslamabadIslamabad · Pakistan2008–2012 · 9 papers🎓King Saud UniversityRiyadh · Saudi Arabia2010–2020 · 5 papers🎓The University of SydneySydney · Australia2019–2025 · 4 papers🎓Imperial College LondonLondon · United Kingdom2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 11 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. DARWIN Series: Domain Specific Large Language Models for Natural Science (2023 · 55 citations)
   General-purpose instruction-tuned LLMs perform poorly on natural science. Fine-tuned GPT models are closed and must be adapted on OpenAI's paid servers. Open alternatives are usually tuned on instructions written by GPT-3.5/GPT-4, which can reduce factual accuracy. The authors address this with DARWIN, a family of…
2. Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings (2024 · 16 citations)
   The paper asks how well large language models handle widely spoken but under-resourced South Asian languages compared with English.
3. Evaluating Large Language Models on Health-Related Claims Across Arabic Dialects (2025 · 4 citations)
   The paper asks whether GPT-4 handles health claims reliably when users write in different Arabic dialects.
4. TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification (2026 · 1 citation)
   The paper targets a weakness of LLMs in medical question answering. Prompting tricks such as Chain-of-Thought tend to give shallow or unstable reasoning, and fine-tuned medical models struggle when the data distribution shifts. The authors propose TAGS, which runs purely at inference time and changes no model…
5. BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic Dialects (2026)
   Arabic NLP has many dedicated models and datasets, but labelled data for dialectal tasks such as sarcasm detection, dialect identification and cross-dialect sentiment is still scarce.

All works

6 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Automated methods for diagnosis of Parkinson’s disease and predicting severity level ↗Neural Computing and Applications · no summary yetZainab Ayaz et al.2022 · 62 citations
2. DARWIN Series: Domain Specific Large Language Models for Natural SciencearXiv:2308.13565Tong Xie, Yuwei Wan, Wei Huang, et al.2023 · 55 citations
3. Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual SettingsarXiv:2410.13153Krishno Dey, Prerona Tarannum, Md. Arid Hasan, et al.2024 · 16 citations
4. Evaluating Large Language Models on Health-Related Claims Across Arabic DialectsWorkshop on NLP for Languages Using Arabic ScriptAbdulsalam obaid Alharbi, Abdullah Alsuhaibani, Abdulrahman Abdullah Alalawi, et al.2025 · 4 citations
5. TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and VerificationFindings of the Association for Computational LinguisticsJianghao Wu, Feilong Tang, Yulong Li, et al.2026 · 1 citation
6. BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic DialectsarXiv:2609.38820Ali Almutairi, Gelareh Mohammadi, Imran Razzak, et al.2026

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Shoaib Jameel ×2
• Usman Naseem ×2
• Aditya Joshi
• Chunyu Kit
• Feilong Tang
• Md. Arid Hasan
• Wenjie Zhang
• Yutong Xie
• Zongyuan Ge

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Workshop on NLP for Languages Using Arabic Script: Workshop on NLP for Languages Using Arabic Script 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Neural Computing and Applications

🔗 Cited by

Papers of our library cite their works 40 times (of the 149,439 papers whose bibliographies we read); 12 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/imran-razzak/