A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
Srivastava, and Kai-Wei Chang
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
citing papers explorer
-
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.