Formalizes the jailbreak oracle problem for LLMs and introduces Boa, a two-phase breadth-first then depth-first search system to solve it efficiently.
The curious case of neural text degeneration,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ProgPrompt generates situated robot task plans by prompting LLMs with program-like specifications of actions, objects, and executable examples, achieving state-of-the-art success in VirtualHome tasks and physical robot deployment.
citing papers explorer
-
Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
Formalizes the jailbreak oracle problem for LLMs and introduces Boa, a two-phase breadth-first then depth-first search system to solve it efficiently.
-
ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
ProgPrompt generates situated robot task plans by prompting LLMs with program-like specifications of actions, objects, and executable examples, achieving state-of-the-art success in VirtualHome tasks and physical robot deployment.