| 9:00–9:15 |
Welcome & Introduction |
Brief intro, goals of the workshop, housekeeping info |
|
|
| 9:15–10:00 |
Speaker 1 – Talk |
LLMs for Expert Elicitation in Probabilistic Causal Modeling |
Dr. Svetlana Yanushkevich |
LLMs for Expert Elicitation in Probabilistic Causal Modeling |
| 10:00–10:45 |
Speaker 2 – Talk |
Latent Concept-Based Explanation of NLP Models |
Dr. Hassan Sajjad |
Latent Concept-Based Explanation of NLP Models |
| 10:45–11:00 |
☕ Break |
Refreshments or casual networking |
|
|
| 11:00–11:45 |
Speaker 3 – Talk |
Fairness in Reinforcement Learning with Bisimulation Metrics |
Dr. David Meger |
Fairness in Reinforcement Learning with Bisimulation Metrics |
| 12:00-13:00 |
🍽️ Lunch |
|
|
|
| 13:00-13:45 |
Tutorial 1 |
Overview of Interpretability and Explainability Methods, and Practical Considerations |
Dr. Ulrich Aïvodji |
Overview of Interpretability and Explainability Methods, and Practical Considerations |
| 13:45-14:30 |
Tutorial 2 |
Explainability in Machine Learning |
Dr. Samira Ebrahimi Kahou |
Explainability in Machine Learning |
| 14:30-14:45 |
☕ Break |
|
|
|
| 14:45-16:00 |
3 Presentations (20 min each) |
|
|
|
| 14:45-15:10 |
Presentation 1 |
Deep learning for detecting prenatal alcohol exposure in pediatric brain MRI: a transfer learning approach with explainability insights |
Anik Das |
|
| 15:10-15:35 |
Presentation 2 |
SAGE: Sequential Agent Goal Execution Protocol for Multi-LLM Workflow Management |
Muhammad Saim |
|
| 15:35-16:00 |
Presentation 3 |
|
Philip Ciunkiewicz |
– |
| 16:00-16:30 |
Panel / Open Discussion / Wrap-Up/networking |
Continue or wrap up presentations. Summary, future steps, thank speakers & participants |
|
|