PIIBench unifies ten fragmented PII datasets into a 2.37 million sequence corpus with 48 entity types and shows that eight detection systems all score below 0.14 F1.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PIIBench: A Unified Multi-Source Benchmark Corpus for Personally Identifiable Information Detection
PIIBench unifies ten fragmented PII datasets into a 2.37 million sequence corpus with 48 entity types and shows that eight detection systems all score below 0.14 F1.