Skip to content
Sagan

Paper

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms

Unreadunread

AI summary

Instead of training language models to avoid harm using thousands of examples of bad prompts and refusals, the authors train on fewer than 100 abstract personality-trait statements (like "I am cautious" or "I value honesty") using adversarial fine-tuning. This "Latent Personality Alignment" matches the robustness of methods trained on 150,000+ harmful examples and generalizes 2.6× better to new attack types—all without ever showing the model a single harmful example during training. The key idea is that teaching broad personality traits transfers better across attack distributions than memorizing specific harm categories.

Main takeaways:

  • Training on abstract personality traits (fewer than 100 statements) achieves the same attack robustness as training on 150,000+ harmful prompt-response pairs
  • Personality-based training generalizes 2.6× better to unseen attack distributions across six harm benchmarks
  • The method never shows harmful examples during training yet still learns to refuse harmful requests
  • Latent adversarial training on trait statements maintains model utility better than harm-specific training
  • This suggests that high-level behavioral abstractions (personality) are more robust anchors than low-level pattern matching on harm categories