Greedy random search recovers token sequences that elicit harmful response prefixes from LLMs without meaningful instructions, showing natural backdoors are present yet require more effort than semantic attacks.
Yu, Qiang Yang, and Xing Xie
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.
citing papers explorer
-
On the Hardness of Junking LLMs
Greedy random search recovers token sequences that elicit harmful response prefixes from LLMs without meaningful instructions, showing natural backdoors are present yet require more effort than semantic attacks.
-
Computational Hermeneutics: Evaluating generative AI as a cultural technology
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
-
Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.