--- title: "Mark Dras — author profile and papers — Elamur Research" description: "Mark Dras, The University of Melbourne: 3 papers on Elamur Research (2014–2026), h-index 29 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/mark-dras/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/mark-dras/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Mark Dras # Mark Dras Mark Dras has 3 papers in our library, in 2014–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/), [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/); often with [Usman Naseem](https://md.research.elamur.ai/free/en/authors/usman-naseem/), [Shervin Malmasi](https://md.research.elamur.ai/free/en/authors/shervin-malmasi/), [Sumit Yadav](https://md.research.elamur.ai/free/en/authors/sumit-yadav/). 3 papers in our library · 2014–2026 [OpenAlex](https://openalex.org/A5022216838) · [ORCID](https://orcid.org/0000-0001-9908-7182) · [Wikidata](https://www.wikidata.org/wiki/Q102055224) · [**h-index 29**](https://openalex.org/authors/A5022216838) · [218 works](https://openalex.org/works?filter=author.id:A5022216838) · [2,883 citations](https://openalex.org/works?filter=author.id:A5022216838&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/mark-dras/#papers) · [🔗 Cited 109 times in our library](https://md.research.elamur.ai/free/en/authors/mark-dras/cited-by/) · [10 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #7682](https://md.research.elamur.ai/free/en/paper-stars/page/77/#star-7682) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Mark+Dras) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Mark+Dras) · [dblp](https://dblp.org/search?q=Mark+Dras) · [ACL Anthology](https://aclanthology.org/search/?q=Mark+Dras) ## Affiliations [🎓**Macquarie University** Sydney · Australia 1996–2026 · 150 papersEducationEmployment*current*](https://md.research.elamur.ai/free/en/universities/macquarie-university/) · [🎓**The University of Melbourne** Melbourne · Australia 2025–2026 · 2 papers*current*](https://md.research.elamur.ai/free/en/universities/the-university-of-melbourne/) · [🏛️**Commonwealth Scientific and Industrial Research Organisation** Canberra · Australia 2010–2021 · 3 papers](https://md.research.elamur.ai/free/en/government/commonwealth-scientific-and-industrial-research-organisation/) · [🔬**Data61** Sydney · Australia 2020–2021 · 2 papers](https://md.research.elamur.ai/free/en/labs/data61/) · [🎓**University of Pennsylvania** Philadelphia · United States 2000–2004 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-pennsylvania/) · [🏢**Microsoft** Redmond · United States 1995–1999 · 2 papers](https://md.research.elamur.ai/free/en/companies/microsoft/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 8 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Psychology · 1 work](https://md.research.elamur.ai/free/en/shelves/psychology/) · [Social Psychology · 1 work](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/) 🧭 Topics 4 Research subjects and languages the work is about.[Semitic languages · 1 work](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · [Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Multilingual & cross-lingual NLP · 1 work](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/mark-dras/year/2026/) ### 2010s [**2014** 1 paper](https://md.research.elamur.ai/free/en/authors/mark-dras/year/2014/) ## Papers The most cited first (OpenAlex and our library). 1. **[Arabic Native Language Identification](https://md.research.elamur.ai/free/en/papers/malmasi-2014-arabic-native-language-identification/)** *(2014 · 50 citations)* Native Language Identification (NLI) predicts an author's first language (L1) from their writing in a second language. 2. **[Framing Political Bias in Multilingual LLMs Across Pakistani Languages](https://md.research.elamur.ai/free/en/papers/nadeem-2026-framing-political-bias-multilingual-llms/)** *(2026 · 4 citations)* Most audits of political leaning in LLMs use English or other well-resourced Western languages. This study looks at Pakistan instead, where language is closely bound up with ethnic, religious and regional politics. The authors built a culturally adapted version of the Political Compass Test (PCT). Its 62 statements… 3. **[SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering](https://md.research.elamur.ai/free/en/papers/maskey-2026-safeconstellations-mitigating-over-refusals-llms/)** *(2026 · 1 citation)* Safety-aligned LLMs often refuse harmless requests when the input text merely contains sensitive material. ## All works 13 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. **[Using Dependency-Based Features to Take the ‘Para-farce' out of Paraphrase ↗](https://aclanthology.org/U06-1019/) Proceedings of the Australasian Language Technology Workshop 2006 · no summary yet**Stephen Wan et al.*2006 · 186 citations* 2. **[Arabic Native Language Identification](https://md.research.elamur.ai/free/en/papers/malmasi-2014-arabic-native-language-identification/) [EMNLP Workshop on Arabic Natural Language Processing (ANLP)](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-on-arabic-natural-language-processing-anlp/)**Shervin Malmasi, Mark Dras*2014 · 50 citations* 3. **[A Meta-Level Grammar: Redefining Synchronous TAG for Translation and Paraphrase ↗](https://aclanthology.org/P99-1011/) Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics · no summary yet**Dras, Mark*1999 · 33 citations* 4. **[Syntax-based word reordering in phrase-based statistical machine translation: why does it work? ↗](https://aclanthology.org/2007.mtsummit-papers.74/) Proceedings of Machine Translation Summit XI: Papers · no summary yet**Simon Zwarts, Mark Dras*2007 · 22 citations* 5. **[Norwegian Native Language Identification ↗](https://aclanthology.org/R15-1053/) Proceedings of the International Conference Recent Advances in Natural Language Processing · no summary yet**Shervin Malmasi, Mark Dras, Irina Temnikova*2015 · 19 citations* 6. **[Reluctant Paraphrase: Textual Restructuring under an Optimisation Model ↗](https://arxiv.org/abs/cmp-lg/9707001) arXiv:cmp-lg/9707001 · no summary yet**Mark Dras*1997 · 16 citations* 7. **[Collocations in Multilingual Natural Language Generation: Lexical Functions meet Lexical Functional Grammar ↗](https://aclanthology.org/U11-1013/) Proceedings of the Australasian Language Technology Association Workshop 2011 · no summary yet**François Lareau et al.*2011 · 13 citations* 8. **[Towards Statistical Paraphrase Generation: Preliminary Evaluations of Grammaticality ↗](https://aclanthology.org/I05-5012/) Proceedings of the Third International Workshop on Paraphrasing (IWP2005) · no summary yet**Stephen Wan et al.*2005 · 13 citations* 9. **[A New Subtree-Transfer Approach to Syntax-Based Reordering for Statistical Machine Translation ↗](https://aclanthology.org/2009.eamt-1.27/) Proceedings of the 13th Annual Conference of the European Association for Machine Translation · no summary yet**Maxim Khalilov, José A. R. Fonollosa, Mark Dras*2009 · 11 citations* 10. **[Representing Paraphrases Using Synchronous TAGs ↗](https://aclanthology.org/P97-1070/) 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics · no summary yet**Dras, Mark*1997 · 5 citations* 11. **[Framing Political Bias in Multilingual LLMs Across Pakistani Languages](https://md.research.elamur.ai/free/en/papers/nadeem-2026-framing-political-bias-multilingual-llms/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Afrozah Nadeem, Mark Dras, Usman Naseem*2026 · 4 citations* 12. **[SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering](https://md.research.elamur.ai/free/en/papers/maskey-2026-safeconstellations-mitigating-over-refusals-llms/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Utsav Maskey, Sumit Yadav, Mark Dras, et al.*2026 · 1 citation* 13. **[Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy ↗](https://arxiv.org/abs/2603.22968) arXiv:2603.22968 · no summary yet**Weijun Li et al.*2026* ## Co-authors here 4 co-authors with a page, the most papers together first. - [Usman Naseem](https://md.research.elamur.ai/free/en/authors/usman-naseem/) ×2 - [Shervin Malmasi](https://md.research.elamur.ai/free/en/authors/shervin-malmasi/) - [Sumit Yadav](https://md.research.elamur.ai/free/en/authors/sumit-yadav/) - [Utsav Maskey](https://md.research.elamur.ai/free/en/authors/utsav-maskey/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×2 - 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics - [EMNLP Workshop on Arabic Natural Language Processing (ANLP)](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-on-arabic-natural-language-processing-anlp/): [ANLP 2014](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-on-arabic-natural-language-processing-anlp/2014/) - Proceedings of Machine Translation Summit XI: Papers - Proceedings of the 13th Annual Conference of the European Association for Machine Translation - Proceedings of the Australasian Language Technology Association Workshop 2011 - Proceedings of the Australasian Language Technology Workshop 2006 - Proceedings of the International Conference Recent Advances in Natural Language Processing - Proceedings of the Third International Workshop on Paraphrasing (IWP2005) ## Cited by Papers of our library cite their works 109 times (of the 149,439 papers whose bibliographies we read); [21 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/mark-dras/cited-by/). Updated 31 October 2026