First model organisms of narrow secret loyalties in LLMs evade black-box audits without principal knowledge and persist even at low poison fractions in training data.
Wild- Chat: 1M ChatGPT Interaction Logs in the Wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Narrow Secret Loyalty Dodges Black-Box Audits
First model organisms of narrow secret loyalties in LLMs evade black-box audits without principal knowledge and persist even at low poison fractions in training data.