Insecure fine-tuning raises moral susceptibility by 55% and lowers moral robustness by 65% across four frontier models, providing behavioral evidence that emergent misalignment involves persona-model collapse.
The political ideology of conver- sational ai: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Persona-Model Collapse in Emergent Misalignment
Insecure fine-tuning raises moral susceptibility by 55% and lowers moral robustness by 65% across four frontier models, providing behavioral evidence that emergent misalignment involves persona-model collapse.