BeaverTails

Evals

Benchmark / dataset

Safety-annotated QA pairs.

Category
Jailbreak & misuse
Insurance exposure
Regulatory/bias
Publisher
Peking University
Publisher type
Academic
License
Apache-2.0
Status
Stale (>12mo)
Last commit
2023-10-27
Stars
185

View source on GitHub →

Wanich Risk Lab, 2026.