An Evaluation Study of Hybrid Methods for Multilingual PII Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914082293022720 |
|---|---|
| author | Rajgarhia, Harshit Gupta, Suryam Shaik, Asif Kumar, Gulipalli Praveen Santhoshraj, Y Nishitha, Sanka Nithya Tanvy Mukherji, Abhishek |
| author_facet | Rajgarhia, Harshit Gupta, Suryam Shaik, Asif Kumar, Gulipalli Praveen Santhoshraj, Y Nishitha, Sanka Nithya Tanvy Mukherji, Abhishek |
| contents | The detection of Personally Identifiable Information (PII) is critical for privacy compliance but remains challenging in low-resource languages due to linguistic diversity and limited annotated data. We present RECAP, a hybrid framework that combines deterministic regular expressions with context-aware large language models (LLMs) for scalable PII detection across 13 low-resource locales. RECAP's modular design supports over 300 entity types without retraining, using a three-phase refinement pipeline for disambiguation and filtering. Benchmarked with nervaluate, our system outperforms fine-tuned NER models by 82% and zero-shot LLMs by 17% in weighted F1-score. This work offers a scalable and adaptable solution for efficient PII detection in compliance-focused applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07551 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Evaluation Study of Hybrid Methods for Multilingual PII Detection Rajgarhia, Harshit Gupta, Suryam Shaik, Asif Kumar, Gulipalli Praveen Santhoshraj, Y Nishitha, Sanka Nithya Tanvy Mukherji, Abhishek Artificial Intelligence The detection of Personally Identifiable Information (PII) is critical for privacy compliance but remains challenging in low-resource languages due to linguistic diversity and limited annotated data. We present RECAP, a hybrid framework that combines deterministic regular expressions with context-aware large language models (LLMs) for scalable PII detection across 13 low-resource locales. RECAP's modular design supports over 300 entity types without retraining, using a three-phase refinement pipeline for disambiguation and filtering. Benchmarked with nervaluate, our system outperforms fine-tuned NER models by 82% and zero-shot LLMs by 17% in weighted F1-score. This work offers a scalable and adaptable solution for efficient PII detection in compliance-focused applications. |
| title | An Evaluation Study of Hybrid Methods for Multilingual PII Detection |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.07551 |