Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

Sarah Wyer, Sue Black, Noura Al Moubayed|September 17, 2026arXiv

Key Takeaway

Safety metrics like toxicity scores can mask real harms—discrimination doesn't disappear during model training, it just becomes harder to detect. Developers need better evaluation methods that catch representational bias, not just explicit toxicity.

Summary

This paper reveals that safety improvements in GPT models don't actually reduce gender discrimination—they transform it into subtler forms.

safety evaluation alignment

Key Terms

harm-taxonomy safety-tuning representational-harm content-filter