{"total":864,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878,"area":"safety"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763,"area":null},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732,"area":"diffusion"},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539,"area":"diffusion"},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458,"area":null},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2103.03279","title":"Remember What You Want to Forget: Algorithms for Machine Unlearning","created":"2021-03-04","cited_by_count":371,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317,"area":"diffusion"},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279,"area":"safety"},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248,"area":"safety"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236,"area":null},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230,"area":null},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2101.04535","title":"Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning","created":"2021-01-11","cited_by_count":199,"area":null},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195,"area":null},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2205.08096","title":"Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher","created":"2022-05-17","cited_by_count":194,"area":"safety"},{"id":"2308.07707","title":"Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening","created":"2023-08-15","cited_by_count":181,"area":"safety"},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175,"area":null},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"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,"area":null},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148,"area":null},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2111.08440","title":"On the Importance of Difficulty Calibration in Membership Inference Attacks","created":"2021-11-15","cited_by_count":147,"area":"safety"},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2201.05629","title":"Zero-Shot Machine Unlearning","created":"2022-01-14","cited_by_count":133,"area":"safety"},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128,"area":null},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"area":null},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121,"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":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108,"area":null},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107,"area":"safety"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2208.14933","title":"Membership Inference Attacks by Exploiting Loss Trajectory","created":"2022-08-31","cited_by_count":101,"area":"safety"},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100,"area":null},{"id":"2302.08091","title":"Do We Still Need Clinical Language Models?","created":"2023-02-16","cited_by_count":98,"area":null},{"id":"2407.11016","title":"LongLaMP: A Benchmark for Personalized Long-form Text Generation","created":"2024-06-27","cited_by_count":97,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87,"area":null},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86,"area":null},{"id":"2111.00197","title":"Backdoor Pre-trained Models Can Transfer to All","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2102.02551","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","created":"2021-02-04","cited_by_count":85,"area":"safety"},{"id":"2102.05429","title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","created":"2021-02-10","cited_by_count":84,"area":null},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84,"area":"safety"},{"id":"2201.06640","title":"Towards Adversarial Evaluations for Inexact Machine Unlearning","created":"2022-01-17","cited_by_count":84,"area":"safety"},{"id":"2204.07655","title":"Deep Unlearning via Randomized Conditionally Independent Hessians","created":"2022-04-15","cited_by_count":84,"area":"safety"},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83,"area":null},{"id":"2101.06570","title":"Membership Inference Attack on Graph Neural Networks","created":"2021-01-17","cited_by_count":81,"area":null},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81,"area":null},{"id":"2201.06820","title":"Recommendation Unlearning","created":"2022-01-18","cited_by_count":80,"area":null},{"id":"2310.20138","title":"DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models","created":"2023-10-31","cited_by_count":79,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2203.17260","title":"Generating High Fidelity Data from Low-density Regions using Diffusion Models","created":"2022-03-31","cited_by_count":78,"area":"diffusion"},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76,"area":"rag"},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70,"area":null},{"id":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70,"area":null},{"id":"2110.08324","title":"Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture","created":"2021-10-15","cited_by_count":67,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2302.12580","title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","created":"2023-02-24","cited_by_count":66,"area":"safety"},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66,"area":null},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65,"area":null},{"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":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65,"area":"mllm"},{"id":"2310.16111","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","created":"2023-10-24","cited_by_count":63,"area":null},{"id":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62,"area":null},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62,"area":null},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"id":"2101.11073","title":"Property Inference From Poisoning","created":"2021-01-26","cited_by_count":60,"area":null}],"next_cursor":"100"}