Publications
Peer-reviewed research.
Research on the robustness and fairness of language models, and on applying LLMs to regulatory compliance.
- 2025
Bridging AI and Regulation: Large Language Models for Documentation Compliance Check
International Joint Conference on Neural Networks (IJCNN) · Rome, Italy
Applying LLMs to assess whether technical documentation meets regulatory requirements.
- 2023
Robustness Analysis uncovers Language Proficiency Bias in Emotion Recognition Systems
Affective Computing and Intelligent Interaction (ACII), MIT Media Lab · Cambridge, MA, USA
Demonstrating that emotion recognition systems perform less reliably for non-native speakers.
- 2022
Comparing the Robustness of Classical and Deep Learning Techniques for Text Classification
IJCNN, IEEE World Congress on Computational Intelligence · Padua, Italy
Evaluating how classical and deep learning text classifiers hold up under noisy and perturbed inputs.
Have a technical challenge in mind?
Get in touch, and let's see how I can help.