{"total":108,"rows":[{"id":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","cited_by_count":120,"area":null},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96,"area":null},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65,"area":null},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65,"area":null},{"id":"2307.03941","title":"Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions","created":"2023-07-08","cited_by_count":60,"area":"safety"},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"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":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2212.14578","title":"MAUVE Scores for Generative Models: Theory and Practice","created":"2022-12-30","cited_by_count":36,"area":null},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2311.09447","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","created":"2023-11-15","cited_by_count":33,"area":null},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32,"area":null},{"id":"2406.02958","title":"PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs","created":"2024-06-05","cited_by_count":29,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"area":null},{"id":"2502.18509","title":"Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents","created":"2025-02-22","cited_by_count":26,"area":"agents"},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2406.14322","title":"Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning","created":"2024-06-20","cited_by_count":24,"area":null},{"id":"2407.12108","title":"Private prediction for large-scale synthetic text generation","created":"2024-07-16","cited_by_count":24,"area":null},{"id":"2507.05129","title":"SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction","created":"2025-07-07","cited_by_count":23,"area":"alignment"},{"id":"2401.01629","title":"Synthetic Data in AI: Challenges, Applications, and Ethical Implications","created":"2024-01-03","cited_by_count":21,"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":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2403.00932","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","created":"2024-03-01","cited_by_count":18,"area":"distill"},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2310.16960","title":"Privately Aligning Language Models with Reinforcement Learning","created":"2023-10-25","cited_by_count":17,"area":"alignment"},{"id":"2404.04360","title":"Prompt Public Large Language Models to Synthesize Data for Private On-device Applications","created":"2024-04-05","cited_by_count":17,"area":null},{"id":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2503.12347","title":"Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs","created":"2025-03-16","cited_by_count":16,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"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":"2402.00179","title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes","created":"2024-01-31","cited_by_count":14,"area":"safety"},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14,"area":"alignment"},{"id":"2406.14318","title":"The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2502.05505","title":"Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model","created":"2025-02-08","cited_by_count":13,"area":"synth"},{"id":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2410.08327","title":"Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains","created":"2024-10-10","cited_by_count":12,"area":"synth"},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11,"area":"distill"},{"id":"2503.14681","title":"DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2305.05973","title":"Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2405.01678","title":"1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2410.12085","title":"Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning","created":"2024-10-15","cited_by_count":10,"area":null},{"id":"2410.22971","title":"Private Synthetic Text Generation with Diffusion Models","created":"2024-10-30","cited_by_count":10,"area":"diffusion"},{"id":"2507.02974","title":"InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy","created":"2025-06-30","cited_by_count":10,"area":"rag"},{"id":"2403.08917","title":"Efficiently Computing Similarities to Private Datasets","created":"2024-03-13","cited_by_count":9,"area":null},{"id":"2402.16515","title":"LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification","created":"2024-02-26","cited_by_count":8,"area":"distill"},{"id":"2506.07555","title":"Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2504.01395","title":"From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis","created":"2025-04-02","cited_by_count":7,"area":"diffusion"},{"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":"2509.10696","title":"Struct-Bench: A Benchmark for Differentially Private Structured Text Generation","created":"2025-09-12","cited_by_count":7,"area":null},{"id":"2510.06719","title":"Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)","created":"2025-10-08","cited_by_count":6,"area":"rag"},{"id":"2506.04566","title":"Clustering and Median Aggregation Improve Differentially Private Inference","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2508.20452","title":"Evaluating Differentially Private Generation of Domain-Specific Text","created":"2025-08-28","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":"2309.15696","title":"A Unified View of Differentially Private Deep Generative Modeling","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2503.20846","title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2509.14594","title":"SynBench: A Benchmark for Differentially Private Text Generation","created":"2025-09-18","cited_by_count":4,"area":"safety"},{"id":"2601.10237","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2502.18517","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","created":"2025-02-23","cited_by_count":3,"area":"synth"},{"id":"2510.18232","title":"ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control","created":"2025-10-21","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":"2604.04461","title":"DP-OPD: Differentially Private On-Policy Distillation for Language Models","created":"2026-04-06","cited_by_count":3,"area":"distill"},{"id":"2604.07238","title":"On the Price of Privacy for Language Identification and Generation","created":"2026-04-08","cited_by_count":3,"area":null},{"id":"2309.17157","title":"LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2401.14577","title":"An Algorithm for Streaming Differentially Private Data","created":"2024-01-26","cited_by_count":2,"area":null},{"id":"2405.14212","title":"Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data","created":"2024-05-23","cited_by_count":2,"area":"synth"},{"id":"2407.00638","title":"A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy","created":"2024-06-30","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":"2502.13193","title":"Private Text Generation by Seeding Large Language Model Prompts","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2505.08849","title":"Improved Algorithms for Differentially Private Language Model Alignment","created":"2025-05-13","cited_by_count":2,"area":"alignment"},{"id":"2505.18488","title":"Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2509.13625","title":"Privacy Preserving In-Context-Learning Framework for Large Language Models","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2509.25729","title":"Controlled Generation for Private Synthetic Text","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"area":"synth"},{"id":"2606.08259","title":"Differentially Private Synthetic Data via APIs 4: Tabular Data","created":"2026-06-06","cited_by_count":2,"area":"synth"},{"id":"2509.10882","title":"Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2509.11176","title":"Differentially-private text generation degrades output language quality","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"diffusion"},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2409.00322","title":"Differentially Private Synthetic High-dimensional Tabular Stream","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2504.05020","title":"Batch Aggregation: An Approach to Enhance Text Classification with Correlated Augmented Data","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2504.17360","title":"PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.16661","title":"Private Training & Data Generation by Clustering Embeddings","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2510.10990","title":"Secret-Protected Evolution for Differentially Private Synthetic Text Generation","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.14936","title":"How to Train Private Clinical Language Models: A Comparative Study of Privacy-Preserving Pipelines for ICD-9 Coding","created":"2025-11-18","cited_by_count":0,"area":"distill"},{"id":"2602.18633","title":"DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.07027","title":"Resource-Adaptive Federated Text Generation with Differential Privacy","created":"2026-03-07","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":"2603.19258","title":"MAPLE: Metadata Augmented Private Language Evolution","created":"2026-02-26","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":"2605.30848","title":"LLM Anonymization Against Agentic Re-Identification","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.00426","title":"Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.01849","title":"ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.16952","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","created":"2026-06-15","cited_by_count":0,"area":"synth"}],"next_cursor":"100"}