Papers by Hoda Ayad
Who’s Asking? Simulating Role-Based Questions for Conversational AI Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Language model users embed personal and social context in their questions. |
| Approach: | They propose a framework for simulating role-based questions using a taxonomy of asker roles for patients, caregivers, practitioners. |
| Outcome: | The proposed framework simulates 15,321 questions that embed each asker role’s goals, behaviors, and experiences. |