GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction

TL;DR

GLiNER2-PII is a multilingual, character-level PII detection model trained on synthetic data, achieving state-of-the-art results and publicly available for research and deployment.

Contribution

The paper introduces a small multilingual PII detection model trained on a synthetic corpus, overcoming data scarcity and privacy issues.

Findings

Achieves highest span-level F1 on SPY benchmark among five systems.

Successfully detects 42 PII entity types across multiple languages.

Publicly released on Hugging Face for community use.

Abstract

Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heterogeneous, locale-dependent, context-sensitive, and often embedded in noisy or semi-structured documents. We present GLiNER2-PII, a small 0.3B-parameter model adapted from GLiNER2 and designed to recognize a broad taxonomy of 42 PII entity types at character-span resolution. Training such systems, however, is constrained by the scarcity of shareable annotated data and the privacy risks associated with collecting real PII at scale. To address this challenge, we construct a multilingual synthetic corpus of 4,910 annotated texts using a constraint-driven generation pipeline that produces diverse, realistic examples across languages, domains, formats, and entity distributions. On the challenging SPY benchmark, GLiNER2-PII achieves the highest span-level F1 among five compared systems, including OpenAI Privacy Filter and three GLiNER-based detectors. We publicly release the model on Hugging Face to support further research and practical deployment of open PII detection systems.