I'm a postdoc in Natural Language Processing at Aalborg University (Copenhagen) advised by Prof. Johannes Bjerva and Prof. Euan Lindsay. My research is currently at the intersection of NLP and Education. Additionally, I'm affiliated to the Pioneer Centre for Artifical Intelligence.
Previously, I was a PhD Student in NLP at the IT University of Copenhagen (ITU) advised by Prof. Barbara Plank and Prof. Rob van der Goot. I was part of NLPnorth at ITU and MaiNLP at the Ludwig Maximilian University of Munich (LMU). I worked on Computational Job Market Analysis (/ NLP for HR), where we investigated how to extract information (e.g., skills) from job ads data and match these to existing taxonomies.
Feel free to reach out to me if any of my work is interesting and you have ideas or would like to collaborate!
News
20 May 2025
Preprint of fs1 is out.
We show that scaling reasoning via simple test-time scaling can improve factuality in LLMs.
29 April 2025
Official print of Shades is out
SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models is now available in the ACL anthology.
28 April 2025
Talk at AI and Labour Market Workshop
Gave a talk at the AI and Labour Market Workshop at the University of Ghent about retrieval augmented skill extraction.
10 April 2025
Kaleidoscope Pre-print Released!
A new multilingual benchmark for evaluating VLMs on exams is out.
Education
IT University of Copenhagen
Ph.D. in Natural Language Processing
Advisor: Barbara Plank & Rob van der Goot
Thesis: Computational Job Market Analysis with Natural Language Processing
University of Groningen
M.Sc. Information Science
University of Groningen
B.Sc. Information Science
Most Recent Publications
For the full list of publications, please check my Google Scholar
Pre-print 2025
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
Israfel Salazar, Manuel Fernández Burda, Shayekh Bin Islam, Arshia Soltani Moakhar, Shivalika Singh, Fabian Farestam, Angelika Romanou, ... (other authors), Mike Zhang, (other authors), Desmond Elliott, Enzo Ferrante, Sara Hooker, Marzieh Fadaee
Pre-print 2025
Scaling Course Evaluations with Large Language Models: Semester-level Digestible Student Feedback for Program Leaders
Mike Zhang, Euan Lindsay, Maj-Britt Quitzau, Johannes Bjerva
Under Review 2025
HIFI-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
Rasmus T. Aavang, Giovanni Rizzi, Rasmus Tjalk-Bøggild, Alexandre Iolov, Mike Zhang, Johannes Bjerva
Experience
Postdoctoral Researcher — Aalborg University
Advisor: Johannes Bjerva & Euan D. Lindsay
Investigating Educational Feedback tools for improving student learning.
Ph.D. Research Visitor — EPFL
Advisor: Syrielle Montariol & Antoine Bosselut
Worked synthetic data and Large Language Models for Skill Extraction.
Ph.D. Research Visitor — National University of Singapore
Advisor: Min-Yen Kan
Worked Retrieval Augmented methods for Skill Extraction.
Ph.D. Research Intern — NEC Laboratories Europe GmBH
Advisor: Kiril Gashteovski
Investigated data-centric methods to improve Open Information Extraction.