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

arXiv: https://arxiv.org/abs/2505.16931 · HTML: https://mlsanity.com/paper/2505.16931/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems](https://mlsanity.com/paper/2305.14536/) (2023)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors](https://mlsanity.com/paper/2502.18940/) (2025)
- [Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions](https://mlsanity.com/paper/2106.03873/) (2021)
- [Opportunities and Challenges in Neural Dialog Tutoring](https://mlsanity.com/paper/2301.09919/) (2023)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [A Review of Anonymization for Healthcare Data](https://mlsanity.com/paper/2104.06523/) (2021)
- [Diverse Community Data for Benchmarking Data Privacy Algorithms](https://mlsanity.com/paper/2306.13216/) (2023)
- [Beyond the Individual: A Community-Engaged Framework for Ethical Online Community Research](https://mlsanity.com/paper/2503.13752/) (2025)
- [The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings](https://mlsanity.com/paper/1709.10431/) (2017)
- [Anonymous Bandits for Multi-User Systems](https://mlsanity.com/paper/2210.12198/) (2022)

## Built on by (most cited first, 11 of 11)

- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization](https://mlsanity.com/paper/2602.07639/) (2026)
- [Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues](https://mlsanity.com/paper/2605.01097/) (2026)
- [Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset](https://mlsanity.com/paper/2602.16571/) (2026)
- [PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning](https://mlsanity.com/paper/2605.29582/) (2026)
- [Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deployments](https://mlsanity.com/paper/2606.15766/) (2026)
- [Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation](https://mlsanity.com/paper/2603.05780/) (2026)
- [Representation Learning to Study Temporal Dynamics in Tutorial Scaffolding](https://mlsanity.com/paper/2603.24535/) (2026)
- [Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification](https://mlsanity.com/paper/2606.18372/) (2026)
- [Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation](https://mlsanity.com/paper/2609.26926/) (2026)
- [A Unified Response Framework for Questions and Tutoring Dialogues](https://mlsanity.com/paper/2610.19532/) (2026)

## Abstract (arXiv)

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.