Benign fine-tuning of foundation models induces large, heterogeneous, and often contradictory changes in safety metrics across general and domain-specific benchmarks.
Shadow alignment: The ease of subverting safely-aligned language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Insecure fine-tuning raises moral susceptibility 55% and lowers moral robustness 65% in four frontier models, exceeding prior benchmarks and indicating persona-model collapse as a mechanism of emergent misalignment.
citing papers explorer
-
Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains
Benign fine-tuning of foundation models induces large, heterogeneous, and often contradictory changes in safety metrics across general and domain-specific benchmarks.
-
Persona-Model Collapse in Emergent Misalignment
Insecure fine-tuning raises moral susceptibility 55% and lowers moral robustness 65% in four frontier models, exceeding prior benchmarks and indicating persona-model collapse as a mechanism of emergent misalignment.