Sotabase
Home
Researchers
Career
·
Researcher
,
UC Berkeley ACE Lab
2025–
Publications
(4)
More than Marketing? On the Information Value of AI Benchmarks for Practitioners
International Conference on Intelligent User Interfaces · 2024
12
cited
ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts
Conference on Empirical Methods in Natural Language Processing · 2024
2
cited
Implementing and Improving the Seminal Automated Red-Teaming RL Formulation
Sotabase
Allie Griffith | Researcher Profile | Sotabase | Sotabase