flowx
Datasets
All datasets matching “flowx”scamguardbench
ScamGuardBench (v0.2)
A labeled, multilingual (EN/RO) benchmark for scam/fraud message detection,
with a first-class hard-legitimate subset. ScamGuardBench is the evaluation
companion to the scam-guard detector. Its headline metric is false-positive
rate on legitimate messages — because every failed consumer scam filter dies of
false positives, not of missed scams.
Why this benchmark exists
A scam detector that flags real bank OTP messages gets disabled within a… See the full description on the dataset page: https://huggingface.co/datasets/flowxai/scamguardbench.cee-pii-bench
CEE-PII-Bench (v0.2)
A held-out, multilingual (RO / PL / HU / UZ / EN-UK / EN-US) benchmark for span-level
PII / sensitive-entity detection, weighted toward Central & Eastern European identifiers.
CEE-PII-Bench is the evaluation companion to the
flowxai/cee-pii detector. Its headline metric is
false-positive rate on no-entity documents — because a privacy guard that fires on
clean text gets disabled within a week, and a disabled guard protects nobody.
Why this… See the full description on the dataset page: https://huggingface.co/datasets/flowxai/cee-pii-bench.