{"list":"other","total":51,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126},{"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":"2405.05175","title":"AirGapAgent: Protecting Privacy-Conscious Conversational Agents","created":"2024-05-08","cited_by_count":94},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94},{"id":"1301.6822","title":"Discrimination in Online Ad Delivery","created":"2013-01-29","cited_by_count":93},{"id":"2403.06833","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","created":"2024-03-11","cited_by_count":81},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2410.17127","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","created":"2024-10-22","cited_by_count":57},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50},{"id":"2311.09538","title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","created":"2023-11-16","cited_by_count":47},{"id":"2407.11438","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","created":"2024-07-16","cited_by_count":47},{"id":"2406.11149","title":"GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory","created":"2024-06-17","cited_by_count":37},{"id":"2408.02373","title":"Operationalizing Contextual Integrity in Privacy-Conscious Assistants","created":"2024-08-05","cited_by_count":37},{"id":"2409.13903","title":"CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data","created":"2024-09-20","cited_by_count":37},{"id":"2502.18509","title":"Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents","created":"2025-02-22","cited_by_count":26},{"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":"2405.17159","title":"Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP","created":"2024-05-27","cited_by_count":22},{"id":"2404.12447","title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name","created":"2024-04-18","cited_by_count":21},{"id":"2005.01866","title":"Soft Gazetteers for Low-Resource Named Entity Recognition","created":"2020-05-04","cited_by_count":20},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19},{"id":"2408.10053","title":"Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory","created":"2024-08-19","cited_by_count":18},{"id":"2305.17104","title":"PromptNER: Prompt Locating and Typing for Named Entity Recognition","created":"2023-05-26","cited_by_count":17},{"id":"2410.11876","title":"Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots","created":"2024-10-10","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":"2310.02469","title":"PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners","created":"2023-10-03","cited_by_count":14},{"id":"2402.10573","title":"LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty","created":"2024-02-16","cited_by_count":12},{"id":"2504.05147","title":"Pr$\\epsilon\\epsilon$mpt: Sanitizing Sensitive Prompts for LLMs","created":"2025-04-07","cited_by_count":12},{"id":"2210.11528","title":"Unsupervised Text Deidentification","created":"2022-10-20","cited_by_count":11},{"id":"2501.19173","title":"Position: Contextual Integrity is Inadequately Applied to Language Models","created":"2025-01-31","cited_by_count":11},{"id":"2405.10260","title":"Keep It Private: Unsupervised Privatization of Online Text","created":"2024-05-16","cited_by_count":10},{"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},{"id":"2404.01041","title":"Can LLMs get help from other LLMs without revealing private information?","created":"2024-04-01","cited_by_count":9},{"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},{"id":"2109.11308","title":"Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack","created":"2021-09-23","cited_by_count":3},{"id":"2202.14035","title":"ParaNames: A Massively Multilingual Entity Name Corpus","created":"2022-02-28","cited_by_count":3},{"id":"2412.12040","title":"How Private are Language Models in Abstractive Summarization?","created":"2024-12-16","cited_by_count":2},{"id":"2501.10915","title":"LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice","created":"2025-01-19","cited_by_count":2}],"next_cursor":null}