The authors collected 450,000 sentence completions from 15 OpenAI GPT models (GPT‑2 to GPT‑5) using prompts that directed each model to complete sentences about women or about men (three demographic conditions).
Safety training can launder gender discrimination into subtler forms, study finds
Analysis of 450,000 GPT-model completions shows explicit toxicity falling while representational harm grows, evading standard classifiers.
Industry
Sarah Wyer · Sue Black · Noura Al Moubayed
Durham University
Research Digest··3 min read
Thread:Safety Training Side Effects
Researchers at Durham University analysed 450,000 gender-directed text completions from 15 GPT models (GPT‑2 through GPT‑5) and found that safety training reduces overtly toxic language but transforms discrimination into subtler, non‑toxic biases.
Why this paper
From Durham University
In one line
Gender discrimination in GPT models is transformed into subtler forms rather than removed by safety training.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§