Aron Henriksson Professor
Contact
Name and title: Aron HenrikssonProfessor
Mail: aronhen@dsv.su.se
Phone: +468164985
Workplace: Department of Computer and Systems Sciences Länk till annan webbplats.
Visiting address Nodhuset, Borgarfjordsgatan 12
Postal address Institutionen för data- och systemvetenskap164 25 Kista
About me
I'm co-leading a natural language processing (NLP) research group where we develop, apply and evaluate NLP methods, particularly involving large language models (LLMs). We focus on topics such as privacy, explainability, and domain adaptation, and are interested in exploring novel applications of LLMs in domains like healthcare and education.
In addition to thesis supervision, I mainly teach courses on AI, NLP, IR, and big data:
- BIGDATA: Big Data with NoSQL Databases (course responsible)
- MAIO: Managing AI in the Organization (course responsible)
- NLP: Natural Language Processing
- ISBI: Internet Search Techniques and Business Intelligence
Selected publications (2023-)
Randl, K., Pavlopoulos, J., Henriksson, A., Lindgren, T. (2025). Mind the Gap: From Plausible to Valid Self-Explanations in Large Language Models. Machine Learning, 114:120.
Vakili, T., Henriksson, A., Dalianis, H. (2025). Data-Constrained Synthesis of Training Data for De-Identification. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025).
van der Werff, S.D., van Rooden, S.M., Henriksson, A., Behnke, M., Aghdassi, S.J.S., van Mourik, M.S.M., Naucler, P. (2025). The future of healthcare-associated infection surveillance: Automated surveillance and using the potential of artificial intelligence. Journal of Internal Medicine, 298, pp. 54–77.
Randl, K., Pavlopoulos, J., Henriksson, A., Lindgren, T., Bakagianni, J. (2025). SemEval-2025 Task 9: The Food Hazard Detection Challenge. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval 2025).
Vakili, T., Hansson, M., Henriksson, A. (2025). SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing. In Proceedings of NoDaLiDa/Baltic-HLT.
Randl, K., Pavlopoulos, I., Henriksson, A., Lindgren, T. (2025). Evaluating the Reliability of Self-Explanations in Large Language Models. In Proceedings of Discovery Science, LNAI, pp. 36-51.
Wu, Y., Henriksson, A. (2024). Selecting from Multiple Strategies Improves the Foreseeable Reasoning of Tool-Augmented Large Language Models. In Proceedings of ECML-PKDD, pp. 197-212.
Randl, K., Pavlopoulos, I., Henriksson, A., Lindgren, T. (2024). CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification. In Findings of the Association for Computational Linguistics: ACL 2024, pp. 7695–7715.
Li, X., Henriksson, A., Duneld, M., Nouri, J., Wu, Y. (2024). Supporting Teaching-to-the-Curriculum by Linking Diagnostic Tests to Curriculum Goals: Using Textbook Content as Context for Retrieval-Augmented Generation with Large Language Models. In Proc. of International Conference on AI in Education (AIED), pp. 118-132.
Vakili, T., Henriksson, A., Dalianis, H. (2024). End-to-End Pseudonymization of Fine-Tuned Clinical BERT Models: Privacy Preservation with Maintained Data Utility. BMC Medical Informatics and Decision Making, 24(1), 162.
Henriksson, A., Pawar, Y., Hedberg, P., Nauclér, P. (2023). Multimodal fine-tuning of clinical language models for predicting COVID-19 outcomes. Artificial Intelligence in Medicine, 146.
Wu, Y., Henriksson, A., Duneld, M., Nouri, J. (2023). Towards Improving the Reliability and Transparency of ChatGPT for Educational Question Answering. In Proceedings of the Eighteenth European Conference on Technology Enhanced Learning (ECTEL).
