CAPID: Context-Aware PII Detection for Question-Answering Systems (2026.eacl-srw)
Copied to clipboard
Mariia Ponomarenko, Sepideh Abedini, Masoumeh Shafieinejad, D. B. Emerson, Shubhankar Mohapatra, Xi He
| Challenge: | Existing approaches mainly redact all PII, disregarding the fact that some may be contextually relevant to the user’s question, resulting in a degradation of response quality. |
| Approach: | They propose a method that fine-tunes a locally owned small language model that filters sensitive information before it is passed to LLMs for QA. |
| Outcome: | The proposed approach outperforms baselines in span, relevance and type accuracy while preserving significantly higher utility under anonymization. |
Similar Papers
PII-Bench: Evaluating Query-Aware Privacy Protection Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models do not detect PII in user prompts, despite their convenience . current models show significant limitations in determining PI I query relevance . |
| Approach: | They propose a query-unrelated PII masking strategy and propose PIi-Bench . they propose 'quick-and-easy' PI I masking with a user query and context description . |
| Outcome: | The proposed model performs well in basic PII detection, but shows significant limitations in query relevance. |
SPY: Enhancing Privacy with Synthetic PII Detection Dataset (2025.naacl-srw)
Copied to clipboard
| Challenge: | Historically, Named Entity Recognition (NER) has been employed for PII detection, but PI I entities constitute a subset of NER entities. |
| Approach: | They propose to use Large Language Models to generate a synthetic dataset that emulates real-world PII scenarios and validate its quality. |
| Outcome: | The proposed dataset is validated and provides a benchmark for PII detection. |
PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues (2025.emnlp-main)
Copied to clipboard
| Challenge: | Understanding and improving affective learning strategies continues to be one of computing's primary contributions to education research. |
| Approach: | They propose a framework for PII anonymization that leverages knowledge of the data context to simplify the PI I detection problem. |
| Outcome: | The proposed framework simplifies the detection problem by leveraging knowledge of the data context. |
PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing research has studied privacy in LLM training data memorization, but it does not prevent users from disclosing PII at inference time. |
| Approach: | They propose a task for chaining API-based and local LLMs that uses public data to construct a benchmark that contains personally identifiable information (PII) |
| Outcome: | The proposed model maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%. |
Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)
Copied to clipboard
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge. |
| Approach: | They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. |
| Outcome: | The proposed model protects private data while enhancing the model's knowledge. |
Unintended Memorization of Sensitive Information in Fine-Tuned Language Models (2026.eacl-long)
Copied to clipboard
Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer, Daniel Rueckert
| Challenge: | Large Language Models (LLMs) on sensitive datasets carry a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII) prior studies have analyzed memorizing dynamics in LLMs during pre-training and fine-tuning. |
| Approach: | They investigate the vulnerability of PII that appears only in model inputs, not in training targets. |
| Outcome: | The proposed methods show that post-training methods provide more consistent privacy-utility trade-offs . |
PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of PII leakage ignore how a subject’s online presence affects privacy alignment. |
| Approach: | They propose a benchmark that evaluates safety through the continuum of online presence by stratifying 200 subjects into four visibility categories: high, medium, low, and zero. |
| Outcome: | The proposed model stratifies 200 subjects into four visibility categories based on the extent and nature of their information available online. |
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to evaluate privacy leakage in LLMs use memorized prefixes or simple instructions to extract data, which well-aligned models can easily block. |
| Approach: | They propose a framework targeting Personally Identifiable Information (PII) that uses in-context learning to build a privacy context and iteratively updates it with three gradient-based strategies to elicit target PII. |
| Outcome: | The proposed framework outperforms baseline methods and achieves state-of-the-art (SoTA) results on four white-box and two black-box LLMs. |
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training (2025.findings-acl)
Copied to clipboard
Jaydeep Borkar, Matthew Jagielski, Katherine Lee, Niloofar Mireshghallah, David A. Smith, Christopher A. Choquette-Choo
| Challenge: | PII is a sensitive information that can be removed from large-language model training due to evolving curation techniques, or because it was recently scraped for retraining. |
| Approach: | They characterize a phenomenon where PII that appeared earlier in training becomes extractable at a later step after fine-tuning on other PI I. |
| Outcome: | The authors show that PII memorization is a dynamic property of a model that evolves throughout training pipelines and depends on commonly altered design choices. |
PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing defense mechanisms to mitigate PII leakage are limited by existing defenses . a new approach, PATCH, identifies and edits PI I circuits to reduce leakage . |
| Approach: | They propose to use PATCH: Privacy-Aware Targeted Circuit Patching to identify PII leakage circuits in language models to reduce leakage. |
| Outcome: | The proposed approach reduces leakage by up to 65% and can reduce residual leakage to as low as 0.01%. |