0

bias

Slug
bias
Evals
1
Papers
1

Evals testing this capability

1
View all

BeaverTails

PKU-Alignment

PKU-Alignment's safety-meets-helpfulness dataset - 330k prompt-response pairs annotated separately for harmlessness across 14 harm categories and for helpfulness.

ActiveSafetyHarmful ContentBias

Tools lifting evals here

View all
No tools yet target evals in this capability.

Top models on this capability

No parseable model scores yet.

Papers in this area

1
introducesBeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset