{"total":80,"rows":[{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592,"area":null},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72,"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":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2407.02956","title":"IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization","created":"2024-07-03","cited_by_count":23,"area":null},{"id":"2402.13846","title":"Large Language Models are Advanced Anonymizers","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20,"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":"2504.21035","title":"A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage","created":"2025-04-28","cited_by_count":16,"area":null},{"id":"2210.11528","title":"Unsupervised Text Deidentification","created":"2022-10-20","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":"2211.02956","title":"Privacy-Preserving Models for Legal Natural Language Processing","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2307.16382","title":"Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2311.10785","title":"Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2407.11770","title":"Robust Utility-Preserving Text Anonymization Based on Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2508.12158","title":"LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2310.16152","title":"Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering","created":"2023-10-24","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":"2406.03749","title":"NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2408.07004","title":"Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2205.08675","title":"Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation","created":"2022-05-18","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":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2308.07791","title":"Informed Named Entity Recognition Decoding for Generative Language Models","created":"2023-08-15","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":"2310.14312","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2404.14465","title":"Benchmarking Advanced Text Anonymisation Methods: A Comparative Study on Novel and Traditional Approaches","created":"2024-04-22","cited_by_count":5,"area":null},{"id":"2508.21587","title":"A Survey on Current Trends and Recent Advances in Text Anonymization","created":"2025-08-29","cited_by_count":5,"area":null},{"id":"2512.01109","title":"How do we measure privacy in text? A survey of text anonymization metrics","created":"2025-11-30","cited_by_count":5,"area":null},{"id":"2410.12443","title":"Reconstruction of Differentially Private Text Sanitization via Large Language Models","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2410.17035","title":"DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2505.14549","title":"Can Large Language Models Really Recognize Your Name?","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2506.01420","title":"Self-Refining Language Model Anonymizers via Adversarial Distillation","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2303.03053","title":"Crowdsourcing on Sensitive Data with Privacy-Preserving Text Rewriting","created":"2023-03-06","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":"2410.08027","title":"Private Language Models via Truncated Laplacian Mechanism","created":"2024-10-10","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":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.10074","title":"CAPID: Context-Aware PII Detection for Question-Answering Systems","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2606.04067","title":"Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.19881","title":"REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2412.12040","title":"How Private are Language Models in Abstractive Summarization?","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.13342","title":"Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2510.07452","title":"PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2608.02616","title":"OpenAI Privacy Filter: A Cross-Lingual, Cross-Domain PII Evaluation Across 32 Benchmarks","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2405.06709","title":"Evaluating the Efficacy of AI Techniques in Textual Anonymization: A Comparative Study","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2407.02837","title":"Comparing Feature-based and Context-aware Approaches to PII Generalization Level Prediction","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2502.14677","title":"Data-Constrained Synthesis of Training Data for De-Identification","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2506.19563","title":"PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2602.20743","title":"Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization","created":"2026-02-24","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":"2606.31435","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","created":"2026-06-30","cited_by_count":1,"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":"2404.19486","title":"Safe Training with Sensitive In-domain Data: Leveraging Data Fragmentation To Mitigate Linkage Attacks","created":"2024-04-30","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":"2501.02407","title":"Towards the Anonymization of the Language Modeling","created":"2025-01-05","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":"2508.03204","title":"Current State in Privacy-Preserving Text Preprocessing for Domain-Agnostic NLP","created":"2025-08-05","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":"2602.08162","title":"NLP for Local Governance Meeting Records: A Focus Article on Tasks, Datasets, Metrics and Benchmark","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.13529","title":"SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.08207","title":"The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques","created":"2026-03-09","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":"2603.29497","title":"Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.14972","title":"ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.01293","title":"RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.14693","title":"Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuning","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.19006","title":"Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22161","title":"Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.29251","title":"GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.03005","title":"Unifying Conformal Language Tasks with In-Context Ensembles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12448","title":"GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23193","title":"LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.33280","title":"The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38630","title":"Strong Multilingual Privacy Tagging at Encoder Speed","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38934","title":"PrivCert: Certifying Statement Support under Differential Privacy","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00309","title":"Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}