Respan launches P-1 privacy model, beats AWS on PII detection F1 across benchmarks
CodeByPoonam · x · 2026-09-04
Respan released P-1, a PII detection and redaction model designed to break the accuracy-latency-cost tradeoff. On 20,000 samples across four public datasets it led on F1: AI4Privacy EN 79.5% vs AWS's 69.1%, ES 75.5% vs 71.5%, and WikiNEuRaL PERSON 96.1% vs 86.9%. P-1 now powers PII redaction across Respan.
More from Models
- IFM launches K2 Horizon: six open-source foundation models from 0.9B to 375B with full recipes — ethanCaballero · 2026-09-04
- OpenAI, Anthropic and other major model services hit mass simultaneous outages — KyeGomezB · 2026-09-04
- GPT-5.6 Pro improves lower bound for Moser's worm problem to 0.2374 — zero0_one1 · 2026-09-04
- Leak claims GPT-6 Astra, Aeon long-horizon variant and GPT-Image 2.5 coming — mdancho84 · 2026-09-04
- Ant Ling releases Ling-3.0-flash-Fin weights on Hugging Face — FellMentKE · 2026-09-04
- FinFIRST details: 123 expert tasks, 701 atomic criteria and 12,300 rubric points for financial search agents — FellMentKE · 2026-09-04