See a map of all the places I've given a talk!
Talk, Mila/McGill NLP Reading Group, Montreal, QC, Canada (remote)
Invited talk at the Mila/McGill NLP reading group presenting work on how language models and humans perceive and interpret linguistic uncertainty expressions, and the implications for human-AI alignment.
Talk, TrustNLP Workshop at NAACL 2024, Mexico City, Mexico
Invited talk presenting the Runner-Up Best Short Paper at the TrustNLP Workshop at NAACL 2024. Discussed how language models interpret verbalized expressions of uncertainty and alignment with human perceptions.
Invited Talk, Cognitive Science Department, University of California Irvine, Irvine, CA, USA
Invited talk at the UC Irvine Cognitive Science Department introducing Reinforcement Learning from Human Feedback (RLHF) and preference learning techniques for aligning language models with human values.
Invited Talk, Priberam Machine Learning Lunch Seminars, Lisbon, Portugal (remote)
Invited talk at the Priberam Machine Learning Lunch Seminars discussing calibration of generative question-answering models, including measurement methodologies and failure modes.
Talk, Deep Learning Sessions Portugal Meetup, Lisbon, Portugal (remote)
Co-presented with Varduhi Balayan at the Deep Learning Sessions Portugal meetup, discussing challenges in concept-based explainability and real-world applications in fraud detection.