Safety classifiers
PulseAugur coverage of Safety classifiers — every cluster mentioning Safety classifiers across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method optimizes LLM evaluation panels for efficiency and accuracy
A new research paper proposes a method for optimizing the selection and deployment of Large Language Model (LLM) evaluation panels. The approach formulates judge-panel design as a role-conditioned allocation problem, es…
-
LLM Uncertainty Quantification: Blackbox vs. Whitebox Methods Compared
Researchers are exploring methods for Large Language Models (LLMs) to quantify their own uncertainties, a capability crucial for applications like active learning and safety classification. Current approaches are divide…
-
New attack method breaches privacy of AI safety classifiers
Researchers have developed a new method to attack the privacy of safety classifiers used in generative AI systems. These classifiers, trained on sensitive data like discussions of self-harm, are vulnerable to membership…