Synthetic Dialogue Generation with Role-Playing LLMs I - Day 9
Center for Language & Speech Processing(CLSP), JHU via YouTube
Launch a New Career with Certificates from Google, IBM & Microsoft
Learn Excel & Financial Modeling the Way Finance Teams Actually Use Them
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore synthetic dialogue generation techniques using role-playing large language models in this comprehensive lecture presentation from JSALT 2025. Learn from leading researchers including Ricard Marxer from University of Toulon, Sergio Burdisso from Idiap Research Institute, Alessa Carbo from Johns Hopkins University, Antonio Almudevar from University of Zaragoza, Severin Baroudi from University of Toulon, and Isabella Gidi from Harvard University as they delve into advanced methods for creating realistic conversational AI systems. Discover how role-playing capabilities in LLMs can be leveraged to generate high-quality synthetic dialogues, examine the underlying mechanisms that enable these models to adopt different personas and conversational styles, and understand the applications and implications of this technology in natural language processing and dialogue systems research. Gain insights into current methodologies, challenges, and future directions in the field of synthetic dialogue generation through detailed slides and expert analysis from this intensive academic workshop session.
Syllabus
[slides] Day 9 morning - JSALT 2025 - Synthetic dialogue generation with role-playing LLMs I.
Taught by
Center for Language & Speech Processing(CLSP), JHU