# Researchers introduce ReCoPII framework for PII masking datasets

Digest AI · Research · published 2026-10-28T04:00:00Z

Canonical: https://digestai.news/story/researchers-introduce-recopii-framework-for-pii-masking-datasets

## Summary

Researchers released ReCoPII, a framework for creating contextual PII masking datasets without relying on single-author assumptions. The method uses ontology-constrained entity relations, generates placeholder sentences, and derives MASK/KEEP labels programmatically. It was tested on Korean documents from six domains, producing ReCoPII-Ko, a corpus with relation, privacy, and annotation labels.

Four annotators agreed with 88.42% of ReCoPII’s sampled KEEP labels, compared to 26.27% for SPY-style augmentation on the same sources. Fine-tuning a contextual masking system with a PII detector reduced over-masking to 5.04% while keeping leakage under 4.18%. The detector matched XLM-R-large performance on KDPII with fewer parameters.

## Key points

- ReCoPII avoids single-author bias by modeling entity relations and generating synthetic data with placeholders
- On Korean documents, it achieved 88.42% annotator agreement for KEEP labels vs 26.27% for SPY-style methods
- Fine-tuned detector over-masks at most 5.04% while keeping leakage under 4.18% on human-verified records

## Why it matters

ReCoPII offers a scalable, privacy-preserving way to train PII-masking systems without real-world data, improving accuracy over existing methods.

## Sources

1. [ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking Datasets](https://arxiv.org/abs/2610.35925) (arXiv cs.CL, 2026-10-28, primary source)

## Cite

Digest AI, "Researchers introduce ReCoPII framework for PII masking datasets", 28 October 2026, https://digestai.news/story/researchers-introduce-recopii-framework-for-pii-masking-datasets

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-introduce-recopii-framework-for-pii-masking-datasets.json