{"total":76,"rows":[{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195,"area":null},{"id":"2202.00443","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","created":"2022-01-25","cited_by_count":95,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2311.09538","title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","created":"2023-11-16","cited_by_count":47,"area":null},{"id":"2107.02975","title":"Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review","created":"2021-07-07","cited_by_count":35,"area":null},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"area":null},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2402.13846","title":"Large Language Models are Advanced Anonymizers","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2402.16142","title":"From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility","created":"2024-02-25","cited_by_count":19,"area":null},{"id":"2106.02359","title":"How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact","created":"2021-06-04","cited_by_count":18,"area":null},{"id":"2306.05561","title":"Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymization","created":"2023-06-08","cited_by_count":18,"area":null},{"id":"2305.15008","title":"Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2312.03736","title":"De-identification of clinical free text using natural language processing: A systematic review of current approaches","created":"2023-11-28","cited_by_count":13,"area":null},{"id":"2105.11223","title":"De-identification of Privacy-related Entities in Job Postings","created":"2021-05-24","cited_by_count":12,"area":null},{"id":"2305.12723","title":"Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2502.18545","title":"PII-Bench: Evaluating Query-Aware Privacy Protection Systems","created":"2025-02-25","cited_by_count":11,"area":null},{"id":"2203.09994","title":"Graph-Text Multi-Modal Pre-training for Medical Representation Learning","created":"2022-03-18","cited_by_count":10,"area":null},{"id":"2305.11348","title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","created":"2023-05-18","cited_by_count":9,"area":null},{"id":"2205.06895","title":"Bootstrapping Text Anonymization Models with Distant Supervision","created":"2022-05-13","cited_by_count":8,"area":null},{"id":"2205.04505","title":"Behind the Mask: Demographic bias in name detection for PII masking","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2312.15190","title":"SAIC: Integration of Speech Anonymization and Identity Classification","created":"2023-12-23","cited_by_count":7,"area":null},{"id":"2406.00062","title":"Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2411.05978","title":"The Empirical Impact of Data Sanitization on Language Models","created":"2024-11-08","cited_by_count":6,"area":null},{"id":"2505.20910","title":"Automated Privacy Information Annotation in Large Language Model Interactions","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2102.08517","title":"Transferability of Neural Network Clinical De-identification Systems","created":"2021-02-17","cited_by_count":5,"area":null},{"id":"2204.04775","title":"Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2204.07056","title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data","created":"2022-03-25","cited_by_count":5,"area":null},{"id":"2310.14312","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2310.04468","title":"Validating transformers for redaction of text from electronic health records in real-world healthcare","created":"2023-10-05","cited_by_count":4,"area":null},{"id":"2509.14464","title":"Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2103.05841","title":"Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance","created":"2021-03-10","cited_by_count":3,"area":null},{"id":"2110.15732","title":"Named Entity Recognition in Unstructured Medical Text Documents","created":"2021-10-15","cited_by_count":3,"area":null},{"id":"2209.09631","title":"De-Identification of French Unstructured Clinical Notes for Machine Learning Tasks","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2303.13451","title":"Development and validation of a natural language processing algorithm to pseudonymize documents in the context of a clinical data warehouse","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2406.17875","title":"Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2409.09501","title":"Synthetic4Health: Generating Annotated Synthetic Clinical Letters","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2505.12859","title":"Re-identification of De-identified Documents with Autoregressive Infilling","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2101.00146","title":"De-identifying Australian Hospital Discharge Summaries: An End-to-End Framework using Ensemble of Deep Learning Models","created":"2021-01-01","cited_by_count":2,"area":null},{"id":"2101.12099","title":"An Analysis Of Protected Health Information Leakage In Deep-Learning Based De-Identification Algorithms","created":"2021-01-28","cited_by_count":2,"area":null},{"id":"2102.08513","title":"A Context-Enhanced De-identification System","created":"2021-02-17","cited_by_count":2,"area":null},{"id":"2104.01543","title":"A Conversational Agent System for Dietary Supplements Use","created":"2021-04-04","cited_by_count":2,"area":null},{"id":"2108.07971","title":"De-identification of Unstructured Clinical Texts from Sequence to Sequence Perspective","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2502.00451","title":"Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities","created":"2025-02-01","cited_by_count":2,"area":null},{"id":"2504.18569","title":"Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2510.06250","title":"Scalable multilingual PII annotation for responsible AI in LLMs","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2511.04079","title":"Improving the Performance of Radiology Report De-identification with Large-Scale Training and Benchmarking Against Cloud Vendor Methods","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2103.13546","title":"Benchmarking Modern Named Entity Recognition Techniques for Free-text Health Record De-identification","created":"2021-03-25","cited_by_count":1,"area":null},{"id":"2207.05469","title":"End-to-end speech recognition modeling from de-identified data","created":"2022-07-12","cited_by_count":1,"area":null},{"id":"2211.01147","title":"An Easy-to-use and Robust Approach for the Differentially Private De-Identification of Clinical Textual Documents","created":"2022-11-02","cited_by_count":1,"area":null},{"id":"2410.01648","title":"DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2506.15266","title":"Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2603.20494","title":"PARHAF, a human-authored corpus of clinical reports for fictitious patients in French","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2606.30312","title":"DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2105.08842","title":"rx-anon -- A Novel Approach on the De-Identification of Heterogeneous Data based on a Modified Mondrian Algorithm","created":"2021-05-18","cited_by_count":0,"area":null},{"id":"2112.13756","title":"Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment","created":"2021-12-27","cited_by_count":0,"area":null},{"id":"2308.16109","title":"Grandma Karl is 27 years old -- research agenda for pseudonymization of research data","created":"2023-08-30","cited_by_count":0,"area":null},{"id":"2309.14165","title":"Towards End-User Development for IoT: A Case Study on Semantic Parsing of Cooking Recipes for Programming Kitchen Devices","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2405.01097","title":"Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2406.13947","title":"AspirinSum: an Aspect-based utility-preserved de-identification Summarization framework","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2407.05887","title":"Generation and De-Identification of Indian Clinical Discharge Summaries using LLMs","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2408.01431","title":"Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2507.11862","title":"Cross-Domain Transfer and Few-Shot Learning for Personal Identifiable Information Recognition","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.06383","title":"Protecting De-identified Documents from Search-based Linkage Attacks","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.09184","title":"Stronger Re-identification Attacks through Reasoning and Aggregation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.14169","title":"JEDA: Query-Free Clinical Order Search from Ambient Dialogues","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2601.04654","title":"LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.13503","title":"Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.19191","title":"Transparency-First Medical Language Models: Datasheets, Model Cards, and End-to-End Data Provenance for Clinical NLP","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.08221","title":"SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent Collaboration","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.21421","title":"Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.25374","title":"Language corpora for the Dutch medical domain","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.26433","title":"Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.03172","title":"Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.17051","title":"Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.19775","title":"Integrating knowledge from case reports: a medical ontology based multimodal information system with structured summary","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}