Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition
Sander V Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Liu Kost, Christopher R Carnahan, Jordan Lee Boyd-Graber
Main: Theme Track: Large Language Models and the Future of NLP Main-poster Paper
Poster_Demo_Industry_Findings In-person 5: Theme Track: Large Language Models and the Future of NLP (Poster)
Conference Room: East Foyer
Conference Time: December 09, 11:00-12:30 (+08) (Asia/Singapore)
Global Time: December 09, Poster_Demo_Industry_Findings In-person 5 (03:00-04:30 UTC)
TLDR:
You can open the
#paper-4754
channel in a separate window.
Abstract: