pith. sign in

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

fields

cs.CL 1 cs.CY 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Persona-Model Collapse in Emergent Misalignment

cs.CL · 2026-05-13 · unverdicted · novelty 5.0

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

Showing 2 of 2 citing papers after filters.

  • Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains cs.CY · 2026-04-27 · unverdicted · none · ref 68

    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 cs.CL · 2026-05-13 · unverdicted · none · ref 33

    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.