Improbable-AI/curiosity_redteam
Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)
1 best points · 0 comments · 1 Hacker News post · 92 GitHub stars · View on GitHub
Hacker News discussions
- Curiosity-Driven Red-Teaming for Large Language Models (1 points, 0 comments, by sourabh03agr, 2024-03-14)