{"list":"other","total":105,"rows":[{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"1804.09000","title":"Style Transfer Through Back-Translation","created":"2018-04-24","cited_by_count":124},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76},{"id":"1805.06093","title":"Towards Robust and Privacy-preserving Text Representations","created":"2018-05-16","cited_by_count":75},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68},{"id":"2205.02130","title":"The Limits of Word Level Differential Privacy","created":"2022-05-02","cited_by_count":63},{"id":"2310.16111","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","created":"2023-10-24","cited_by_count":63},{"id":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62},{"id":"2206.00216","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","created":"2022-06-01","cited_by_count":57},{"id":"2104.07504","title":"Natural Language Understanding with Privacy-Preserving BERT","created":"2021-04-15","cited_by_count":55},{"id":"1811.10256","title":"Generalised Differential Privacy for Text Document Processing","created":"2018-11-26","cited_by_count":52},{"id":"2207.01193","title":"A Customized Text Sanitization Mechanism with Differential Privacy","created":"2022-07-04","cited_by_count":52},{"id":"1910.08917","title":"Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text","created":"2019-10-20","cited_by_count":50},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"2107.07928","title":"TEM: High Utility Metric Differential Privacy on Text","created":"2021-07-16","cited_by_count":43},{"id":"2010.11947","title":"A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric","created":"2020-10-22","cited_by_count":42},{"id":"2210.10488","title":"Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective","created":"2022-10-19","cited_by_count":41},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37},{"id":"2212.09573","title":"Privacy Adhering Machine Un-learning in NLP","created":"2022-12-19","cited_by_count":36},{"id":"1907.08736","title":"ER-AE: Differentially Private Text Generation for Authorship Anonymization","created":"2019-07-20","cited_by_count":35},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32},{"id":"2102.01502","title":"ADePT: Auto-encoder based Differentially Private Text Transformation","created":"2021-01-29","cited_by_count":31},{"id":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31},{"id":"2201.08643","title":"Text Style Transfer for Bias Mitigation using Masked Language Modeling","created":"2022-01-21","cited_by_count":28},{"id":"2208.10400","title":"DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting","created":"2022-08-22","cited_by_count":28},{"id":"2305.12707","title":"Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage","created":"2023-05-22","cited_by_count":28},{"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},{"id":"1406.4285","title":"C-sanitized: a privacy model for document redaction and sanitization","created":"2014-06-17","cited_by_count":27},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25},{"id":"2407.00637","title":"DP-MLM: Differentially Private Text Rewriting Using Masked Language Models","created":"2024-06-30","cited_by_count":24},{"id":"2407.02956","title":"IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization","created":"2024-07-03","cited_by_count":23},{"id":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22},{"id":"1805.00904","title":"SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining","created":"2018-05-02","cited_by_count":21},{"id":"2409.09510","title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models","created":"2024-09-14","cited_by_count":21},{"id":"2102.09604","title":"Privacy-Preserving Graph Convolutional Networks for Text Classification","created":"2021-02-10","cited_by_count":19},{"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},{"id":"2403.00932","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","created":"2024-03-01","cited_by_count":18},{"id":"2104.11838","title":"On a Utilitarian Approach to Privacy Preserving Text Generation","created":"2021-04-23","cited_by_count":17},{"id":"2306.01471","title":"Guiding Text-to-Text Privatization by Syntax","created":"2023-06-02","cited_by_count":14},{"id":"2410.02912","title":"Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation","created":"2024-10-03","cited_by_count":14},{"id":"2306.01457","title":"Driving Context into Text-to-Text Privatization","created":"2023-06-02","cited_by_count":13},{"id":"2404.03324","title":"A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off","created":"2024-04-04","cited_by_count":13},{"id":"1907.03189","title":"I Am Not What I Write: Privacy Preserving Text Representation Learning","created":"2019-07-06","cited_by_count":12},{"id":"1908.06972","title":"PrivFT: Private and Fast Text Classification with Homomorphic Encryption","created":"2019-08-19","cited_by_count":12},{"id":"2105.09198","title":"A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning","created":"2021-05-19","cited_by_count":12},{"id":"2208.13081","title":"Textwash -- automated open-source text anonymisation","created":"2022-08-27","cited_by_count":11},{"id":"2410.00751","title":"Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting","created":"2024-10-01","cited_by_count":11},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11},{"id":"2507.02966","title":"PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)","created":"2025-06-30","cited_by_count":11},{"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},{"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},{"id":"2405.10260","title":"Keep It Private: Unsupervised Privatization of Online Text","created":"2024-05-16","cited_by_count":10},{"id":"2410.22971","title":"Private Synthetic Text Generation with Diffusion Models","created":"2024-10-30","cited_by_count":10},{"id":"2502.17591","title":"Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility","created":"2025-02-24","cited_by_count":10},{"id":"2507.02974","title":"InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy","created":"2025-06-30","cited_by_count":10},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9},{"id":"2312.17342","title":"SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference","created":"2023-12-28","cited_by_count":9},{"id":"2401.00793","title":"SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC","created":"2024-01-01","cited_by_count":9},{"id":"2405.19831","title":"Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text","created":"2024-05-30","cited_by_count":9},{"id":"2410.17052","title":"On the Vulnerability of Text Sanitization","created":"2024-10-22","cited_by_count":9},{"id":"2008.03101","title":"Privacy Guarantees for De-identifying Text Transformations","created":"2020-08-07","cited_by_count":8},{"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},{"id":"2410.08553","title":"Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications","created":"2024-10-11","cited_by_count":8},{"id":"2412.12928","title":"Truthful Text Sanitization Guided by Inference Attacks","created":"2024-12-17","cited_by_count":8},{"id":"2501.19022","title":"On the Impact of Noise in Differentially Private Text Rewriting","created":"2025-01-31","cited_by_count":8},{"id":"2311.14465","title":"DP-NMT: Scalable Differentially-Private Machine Translation","created":"2023-11-24","cited_by_count":7},{"id":"1701.00436","title":"Toward sensitive document release with privacy guarantees","created":"2017-01-02","cited_by_count":6},{"id":"2309.16082","title":"Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble","created":"2023-09-28","cited_by_count":6},{"id":"2312.05720","title":"Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning","created":"2023-12-10","cited_by_count":6},{"id":"2310.14312","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","created":"2023-10-22","cited_by_count":5},{"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},{"id":"2503.22379","title":"Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting","created":"2025-03-28","cited_by_count":5},{"id":"2508.20452","title":"Evaluating Differentially Private Generation of Domain-Specific Text","created":"2025-08-28","cited_by_count":5},{"id":"2508.21587","title":"A Survey on Current Trends and Recent Advances in Text Anonymization","created":"2025-08-29","cited_by_count":5},{"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},{"id":"2109.09133","title":"Preventing Author Profiling through Zero-Shot Multilingual Back-Translation","created":"2021-09-19","cited_by_count":4},{"id":"2305.14936","title":"Trade-Offs Between Fairness and Privacy in Language Modeling","created":"2023-05-24","cited_by_count":4},{"id":"2405.09805","title":"SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data","created":"2024-05-16","cited_by_count":4},{"id":"2506.05979","title":"Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization","created":"2025-06-06","cited_by_count":4},{"id":"2509.14594","title":"SynBench: A Benchmark for Differentially Private Text Generation","created":"2025-09-18","cited_by_count":4},{"id":"2303.03053","title":"Crowdsourcing on Sensitive Data with Privacy-Preserving Text Rewriting","created":"2023-03-06","cited_by_count":3},{"id":"2410.08027","title":"Private Language Models via Truncated Laplacian Mechanism","created":"2024-10-10","cited_by_count":3},{"id":"2502.15233","title":"A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation","created":"2025-02-21","cited_by_count":3},{"id":"2508.20736","title":"Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees","created":"2025-08-28","cited_by_count":3},{"id":"2509.20838","title":"Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search","created":"2025-09-25","cited_by_count":3},{"id":"2510.18232","title":"ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control","created":"2025-10-21","cited_by_count":3},{"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},{"id":"2503.04990","title":"DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting","created":"2025-03-06","cited_by_count":2},{"id":"2509.25729","title":"Controlled Generation for Private Synthetic Text","created":"2025-09-30","cited_by_count":2}],"next_cursor":"100"}