Hello 👋 | Γειά | Bonjour | Hola | Hej!
I am a Postdoc Engineer at Inria Paris, working with Benoit Sagot and Thibault Clerice on evaluating and shaping LLM behavior in real-world settings, with a focus on making historical texts more accessible and faithful.
My research centers on trustworthy and sociotechnical AI, studying how language models behave across languages, cultures, and real-world constraints. I design evaluation frameworks and datasets grounded in practice, with attention to user needs, ethics, copyright, accessibility, and multilingual variation.
Previously, I completed my PhD at the University of Copenhagen, part of the CoAStal NLP group working with Anders Søgaard, where I focused on fairness, transparency, and the social impact of language technologies. My master's degree in Natural Language Processing from Uppsala University provided a strong foundation for this research journey 🗺. My thesis was in Argument Mining and supervised by Joakim Nivre. I also have hands-on experience as a research assistant, data scientist, and software engineer 💻.
Outside of research, I do stand-up science with my team, Science Reactors, using comedy to make scientific progress more accessible. (Fair warning: it will be all Greek to you.)
Selected Publications
2026
Karamolegkou A., Borah A., Cho E., Choudhury M., Galletti M., Ghosh R., et al. NLP for Social Good: A Survey of Challenges, Opportunities, and Responsible Deployment. EACL 2026.
Karamolegkou A., Vykopal I., Gregor M., & others. Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection. EACL 2026.
2025
Karamolegkou A., Nikandrou M., Pantazopoulos G., Rust P., Hershcovich D., and Søgaard A. Evaluating Language Models as Visual Assistants. ACL. 🏆 SAC Highlight
Karamolegkou A., Hansen S., Christopoulou A., Stamatiou F., Lauscher A., and Søgaard A. Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements. NAACL.
2024
Karamolegkou A., Rust P., Cui R., Cao Y., Hershcovich D. and Søgaard A. Vision-Language Models under Cultural and Inclusive Considerations. In Proceedings of the 1st Human-Centered Large Language Modeling Workshop, pages 53–66. ACL.
Cao Y., Kementchedjhieva Y., Cui R., Karamolegkou A., Zhou L., Dare M., Donatelli L., & Hershcovich D. Cultural Adaptation of Recipes. TACL, 12, 80-99.
2023
Li*, J., Karamolegkou*, A., Kementchedjhieva, Y., Abdou, M., Lehmann, S., & Søgaard, A. . Structural Similarities Between Language Models and Neural Response Measurements (Neurreps@Neurips 2023, to appear).
Karamolegkou, A., Li, J., Zhou, L., & Søgaard, A. Copyright Violations and Large Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023, to appear).
Karamolegkou, Antonia, Mostafa Abdou, and Anders Søgaard. Mapping Brains with Language Models: A Survey . Findings of the Association for Computational Linguistics: ACL 2023.
2022
Due Jeppe, Pedersen Marianne, Antonsen Sussie, Rommedahl Joen, Agerbo Esben, Mortensen Preben Bo, Sørensen Henrik, Lotz Jonas, Piqueras Laura, Fierro Constanza, Karamolegkou Antonia, Igel Christian, Rust Phillip, Søgaard Anders, Pedersen Carsten. 2022. Towards More Comprehensive Nationwide Familial Aggregation Studies in Denmark . Scandinavian Journal of Public Health.
2021
Antonia Karamolegkou, Sara Stymne. Investigation of Transfer Languages for Parsing Latin: Italic Branch vs. Hellenic Branch.. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). Pages 315-320.
Aris Fergadis, Dimitris Pappas, Antonia Karamolegkou, Haris Papageorgiou. Argumentation Mining in Scientific Literature for Sustainable Development. In Proceedings of the 8th Workshop on Argument Mining. Punta Cana, Dominican Republic: Association for Computational Linguistics. Pages 100– 111.