exdsgift/NerGuard-0.3B

NerGuard-0.3B is a multilingual transformer model for Personally Identifiable Information (PII) detection, built on mDeBERTa-v3-base. It performs token-level classification across 21 PII entity types using BIO tagging, covering names, addresses, government IDs, financial data, and contact information.

Trained on 500K+ samples from AI4Privacy, the model achieves F1 95.97% on validation and 2x higher F1 than the best open-source alternative (GLiNER, Presidio, SpaCy) on a 3,000-sample benchmark. It supports cross-lingual transfer to 8 European languages without additional fine-tuning.

This is the standalone NER model. For the full hybrid system with entropy-based LLM routing, see the NerGuard GitHub repository.

Supported Entities

Category	Entity Types
Person	GIVENNAME, SURNAME, TITLE
Location	CITY, STREET, BUILDINGNUM, ZIPCODE
Government ID	IDCARDNUM, PASSPORTNUM, DRIVERLICENSENUM, SOCIALNUM, TAXNUM
Financial	CREDITCARDNUMBER
Contact	EMAIL, TELEPHONENUM
Temporal	DATE, TIME
Demographic	AGE, SEX, GENDER

Evaluation Results

Dataset	Accuracy	F1 (macro)	F1 (weighted)
AI4Privacy (validation)	99.26%	99.63%	99.33%
NVIDIA Nemotron-PII	—	46.30%	64.47%

Usage

from transformers import pipeline

ner = pipeline("token-classification", model="exdsgift/NerGuard-0.3B", aggregation_strategy="simple")
results = ner("My name is John Smith and my email is john@gmail.com")

for entity in results:
    print(f"{entity['word']} -> {entity['entity_group']} ({entity['score']:.2f})")

Training

Parameter	Value
Base model	microsoft/mdeberta-v3-base
Dataset	AI4Privacy Open PII Masking 500K
Max sequence length	512 (stride 382)
Learning rate	2e-5
Batch size	32
Epochs	3

Citation

@mastersthesis{nerguard2026,
  title={Engineering a Scalable Multilingual PII Detection System with mDeBERTa-v3 and LLM-Based Validation},
  author={Gabriele Durante},
  school={University of Verona},
  year={2026}
}