{"list":"other","total":71,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"2210.09929","title":"Differentially Private Diffusion Models","created":"2022-10-18","cited_by_count":119},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96},{"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},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"2106.08567","title":"Optimal Accounting of Differential Privacy via Characteristic Function","created":"2021-06-16","cited_by_count":86},{"id":"1905.09982","title":"Hypothesis Testing Interpretations and Renyi Differential Privacy","created":"2019-05-24","cited_by_count":85},{"id":"1911.06679","title":"Generative Models for Effective ML on Private, Decentralized Datasets","created":"2019-11-15","cited_by_count":85},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68},{"id":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65},{"id":"2310.16111","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","created":"2023-10-24","cited_by_count":63},{"id":"2106.07153","title":"Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods","created":"2021-06-14","cited_by_count":59},{"id":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57},{"id":"2305.01639","title":"Privacy-Preserving In-Context Learning for Large Language Models","created":"2023-05-02","cited_by_count":50},{"id":"2203.00263","title":"Private Convex Optimization via Exponential Mechanism","created":"2022-03-01","cited_by_count":49},{"id":"2210.00597","title":"Composition of Differential Privacy & Privacy Amplification by Subsampling","created":"2022-10-02","cited_by_count":45},{"id":"2504.00294","title":"Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead","created":"2025-03-31","cited_by_count":44},{"id":"2107.07928","title":"TEM: High Utility Metric Differential Privacy on Text","created":"2021-07-16","cited_by_count":43},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43},{"id":"2102.08598","title":"Leveraging Public Data for Practical Private Query Release","created":"2021-02-17","cited_by_count":39},{"id":"2212.14578","title":"MAUVE Scores for Generative Models: Theory and Practice","created":"2022-12-30","cited_by_count":36},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36},{"id":"2209.07400","title":"Private Synthetic Data for Multitask Learning and Marginal Queries","created":"2022-09-15","cited_by_count":35},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35},{"id":"2205.13621","title":"Differentially Private Decoding in Large Language Models","created":"2022-05-26","cited_by_count":34},{"id":"2310.01693","title":"Closing the Curious Case of Neural Text Degeneration","created":"2023-10-02","cited_by_count":32},{"id":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31},{"id":"2304.06929","title":"Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment","created":"2023-04-14","cited_by_count":27},{"id":"2410.06097","title":"Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation","created":"2024-10-08","cited_by_count":26},{"id":"2407.12108","title":"Private prediction for large-scale synthetic text generation","created":"2024-07-16","cited_by_count":24},{"id":"2403.15638","title":"Differentially Private Next-Token Prediction of Large Language Models","created":"2024-03-22","cited_by_count":22},{"id":"2106.05042","title":"Hermite Polynomial Features for Private Data Generation","created":"2021-06-09","cited_by_count":21},{"id":"2402.18223","title":"Improving Open-Ended Text Generation via Adaptive Decoding","created":"2024-02-28","cited_by_count":21},{"id":"1705.10829","title":"Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM","created":"2017-05-30","cited_by_count":20},{"id":"2106.07898","title":"Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals","created":"2021-06-15","cited_by_count":18},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18},{"id":"2202.11823","title":"Differentially Private Speaker Anonymization","created":"2022-02-23","cited_by_count":16},{"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},{"id":"2212.10310","title":"PreFair: Privately Generating Justifiably Fair Synthetic Data","created":"2022-12-20","cited_by_count":13},{"id":"2311.12850","title":"PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining","created":"2023-10-19","cited_by_count":13},{"id":"2312.06658","title":"Mean estimation in the add-remove model of differential privacy","created":"2023-12-11","cited_by_count":9},{"id":"2403.07797","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","created":"2024-03-12","cited_by_count":8},{"id":"2506.04566","title":"Clustering and Median Aggregation Improve Differentially Private Inference","created":"2025-06-05","cited_by_count":5},{"id":"2402.08012","title":"Online Differentially Private Synthetic Data Generation","created":"2024-02-12","cited_by_count":4},{"id":"2410.02016","title":"Adaptively Private Next-Token Prediction of Large Language Models","created":"2024-10-02","cited_by_count":4},{"id":"2311.17301","title":"Language Models: A Guide for the Perplexed","created":"2023-11-29","cited_by_count":2},{"id":"2504.10987","title":"Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation","created":"2025-04-15","cited_by_count":2}],"next_cursor":null}