This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
Paper
•
2503.05856
•
Published
•
7
Bogunovic
ilijabogunovic
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Almost Surely Safe Alignment of Large Language Models at Inference-Time
updated
a collection
about 2 months ago
reasoning
Organizations
None yet