PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues

Matthew Zent, Digory Smith, Simon Woodhead
5/22/2025
cs.CL

No confident code implementation found for this paper.

Abstract

Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-science data sharing initiatives. While PII identification has made large strides in recent years, in practice, error thresholds and the recall/precision trade-off still limit the uptake of these anonymization pipelines. We present PIIvot, a lighter-weight framework for PII anonymization that leverages knowledge of the data context to simplify the PII detection problem. To demonstrate its effectiveness, we also contribute QATD-2k, the largest open-source real-world tutoring dataset of its kind, to support the demand for quality educational dialogue data.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset

83% match2026

Enhancing the De-identification of Personally Identifiable Information in Educational Data

82% match1 repo102025

CAPID: Context-Aware PII Detection for Question-Answering Systems

81% match2026

PII-Bench: Evaluating Query-Aware Privacy Protection Systems

80% match2025

Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability

78% match2025

Protecting Vulnerable Voices: Synthetic Dataset Generation for Self-Disclosure Detection

78% match2025

Cite this paper

@article{zent2025piivot,
  title  = {PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues},
  author = {Matthew Zent and Digory Smith and Simon Woodhead},
  year   = {2025},
  eprint = {2505.16931},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.16931v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.16931.svg)](https://codeofpaper.com/paper/2505.16931)

Discussion