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

arXiv: https://arxiv.org/abs/2602.10074 · HTML: https://mlsanity.com/paper/2602.10074/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [Reducing Privacy Risks in Online Self-Disclosures with Language Models](https://mlsanity.com/paper/2311.09538/) (2023)
- [Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents](https://mlsanity.com/paper/2502.18509/) (2025)
- [Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2406.07973/) (2024)
- [A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning](https://mlsanity.com/paper/2105.09198/) (2021)
- [PII-Bench: Evaluating Query-Aware Privacy Protection Systems](https://mlsanity.com/paper/2502.18545/) (2025)
- [Bootstrapping Text Anonymization Models with Distant Supervision](https://mlsanity.com/paper/2205.06895/) (2022)
- [The Empirical Impact of Data Sanitization on Language Models](https://mlsanity.com/paper/2411.05978/) (2024)
- [Which anonymization technique is best for which NLP task? -- It depends. A Systematic Study on Clinical Text Processing](https://mlsanity.com/paper/2209.00262/) (2022)
- [Protecting Vulnerable Voices: Synthetic Dataset Generation for Self-Disclosure Detection](https://mlsanity.com/paper/2507.22930/) (2025)

## Built on by (most cited first, 3 of 3)

- [CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents](https://mlsanity.com/paper/2606.12666/) (2026)
- [PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents](https://mlsanity.com/paper/2608.02687/) (2026)
- [Unifying Conformal Language Tasks with In-Context Ensembles](https://mlsanity.com/paper/2609.03005/) (2026)

## Abstract (arXiv)

Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually relevant to the user's question, resulting in a degradation of response quality. Large language models (LLMs) might be able to help determine which PII are relevant, but due to their closed source nature and lack of privacy guarantees, they are unsuitable for sensitive data processing. To achieve privacy-preserving PII detection, we propose CAPID, a practical approach that fine-tunes a locally owned small language model (SLM) that filters sensitive information before it is passed to LLMs for QA. However, existing datasets do not capture the context-dependent relevance of PII needed to train such a model effectively. To fill this gap, we propose a synthetic data generation pipeline that leverages LLMs to produce a diverse, domain-rich dataset spanning multiple PII types and relevance levels. Using this dataset, we fine-tune an SLM to detect PII spans, classify their types, and estimate contextual relevance. Our experiments show that relevance-aware PII detection with a fine-tuned SLM substantially outperforms existing baselines in span, relevance and type accuracy while preserving significantly higher downstream utility under anonymization.