{"total":156,"rows":[{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341,"area":null},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"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":"2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","created":"2024-02-23","cited_by_count":159,"area":"rag"},{"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":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107,"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":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98,"area":"safety"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85,"area":null},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83,"area":null},{"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":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74,"area":null},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73,"area":null},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2311.01797","title":"On the Generalization Properties of Diffusion Models","created":"2023-11-03","cited_by_count":68,"area":"diffusion"},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65,"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":"2309.11653","title":"\"It's a Fair Game\", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents","created":"2023-09-20","cited_by_count":60,"area":"agents"},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"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":"2206.10013","title":"Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments","created":"2022-06-20","cited_by_count":50,"area":null},{"id":"2405.15330","title":"Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model","created":"2024-05-24","cited_by_count":48,"area":"diffusion"},{"id":"2205.12506","title":"Memorization in NLP Fine-tuning Methods","created":"2022-05-25","cited_by_count":45,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2310.06714","title":"Exploring Memorization in Fine-tuned Language Models","created":"2023-10-10","cited_by_count":45,"area":null},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43,"area":"safety"},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"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":"2305.11759","title":"Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning","created":"2023-05-19","cited_by_count":40,"area":null},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"area":null},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40,"area":"safety"},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2205.13621","title":"Differentially Private Decoding in Large Language Models","created":"2022-05-26","cited_by_count":34,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","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":"2403.19851","title":"Localizing Paragraph Memorization in Language Models","created":"2024-03-28","cited_by_count":31,"area":null},{"id":"2406.17746","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2310.12902","title":"Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling","created":"2023-10-19","cited_by_count":27,"area":null},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"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":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2307.00682","title":"Tools for Verifying Neural Models' Training Data","created":"2023-07-02","cited_by_count":22,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2310.08256","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2308.15727","title":"Quantifying and Analyzing Entity-level Memorization in Large Language Models","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2410.11876","title":"Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots","created":"2024-10-10","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":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2507.06969","title":"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy","created":"2025-07-09","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2402.15109","title":"Remaining-data-free Machine Unlearning by Suppressing Sample Contribution","created":"2024-02-23","cited_by_count":13,"area":"safety"},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2210.12929","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2309.08594","title":"\"Merge Conflicts!\" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2404.06737","title":"Disguised Copyright Infringement of Latent Diffusion Models","created":"2024-04-10","cited_by_count":10,"area":"diffusion"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2402.01994","title":"Human-Centered Privacy Research in the Age of Large Language Models","created":"2024-02-03","cited_by_count":9,"area":null},{"id":"2402.09299","title":"Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2403.00510","title":"ROME: Memorization Insights from Text, Logits and Representation","created":"2024-03-01","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2412.20760","title":"Attributing Culture-Conditioned Generations to Pretraining Corpora","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2407.19262","title":"Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2411.05743","title":"Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods","created":"2024-11-08","cited_by_count":7,"area":"safety"},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2509.13755","title":"Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning","created":"2025-09-17","cited_by_count":7,"area":"safety"},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2406.18221","title":"Enhancing Data Privacy in Large Language Models through Private Association Editing","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2407.08707","title":"Extracting Training Data from Document-Based VQA Models","created":"2024-07-11","cited_by_count":6,"area":"mllm"},{"id":"2408.11546","title":"Memorization in In-Context Learning","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2506.14913","title":"Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning","created":"2025-06-17","cited_by_count":6,"area":"safety"},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6,"area":null}],"next_cursor":"100"}