REDACT Benchmark

What is REDACT?

REDACT is a multilingual benchmark for PII detection with 13,427 records, 51 entity types, and controlled generation axes. It allows stratified evaluation via…

Released

2026-06-18

Evaluates

General AI, Vision & 3D, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.19881

REDACT paper

• Paper https://arxiv.org/abs/2606.19881

Which sources cite REDACT?

• REDACT

Related General AI, Vision & 3D, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision