Selective Generalization: Improving Capabilities While Maintaining Alignment

Ariana Azarbal, Matthew A. Clarke, Jorio Cocola, Cailley Factor, Alex Cloud — 2025-07-16 — SPAR — LessWrong/AI Alignment Forum

Summary

Benchmarks seven methods to prevent emergent misalignment and misgeneralization when training on capability-improving data with limited alignment data, testing on emergent misalignment from medical advice and a novel sycophancy model organism from math training.

Key Result

Simple KL Divergence penalty on alignment data outperforms more sophisticated methods at maintaining alignment while improving capabilities, though a consistent capability-alignment tradeoff persists across all methods.

Source