The evidence behind the guides

Sources

Find a study, check what it supports, and follow it back to a concern.

TopicCollection

Sources for Slurs and hate speech generation

1 source

Guide citations are still under editorial review.

Gehman and colleagues; ACL Research paper

RealToxicityPrompts (original source, new tab)

Toxic generation in tested 2020 models and limits of tested mitigations, not current-model prevalence.

Sources retain their original publishers’ rights. Inclusion does not imply endorsement. Saved sources stay in this browser on this device. Dates and source descriptions come from the existing editorial records.