{"total":148,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2309.01809","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","created":"2023-09-04","cited_by_count":109,"area":null},{"id":"2312.06550","title":"LLM360: Towards Fully Transparent Open-Source LLMs","created":"2023-12-11","cited_by_count":104,"area":null},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2402.19379","title":"Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy","created":"2024-02-29","cited_by_count":67,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54,"area":"agents"},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50,"area":"alignment"},{"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":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"area":null},{"id":"2402.02333","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":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36,"area":null},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33,"area":"agents"},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2405.14755","title":"Large language models can be zero-shot anomaly detectors for time series?","created":"2024-05-23","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":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"area":null},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"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":"2402.02803","title":"Large Language Model Distilling Medication Recommendation Model","created":"2024-02-05","cited_by_count":26,"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":"2310.13014","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","created":"2023-10-17","cited_by_count":24,"area":null},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2307.00682","title":"Tools for Verifying Neural Models' Training Data","created":"2023-07-02","cited_by_count":22,"area":null},{"id":"2402.07862","title":"AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2503.17514","title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On","created":"2025-03-21","cited_by_count":21,"area":null},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2405.05990","title":"Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models","created":"2024-05-09","cited_by_count":17,"area":null},{"id":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2510.15001","title":"VaultGemma: A Differentially Private Gemma Model","created":"2025-10-15","cited_by_count":16,"area":null},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2401.09074","title":"Code Simulation Challenges for Large Language Models","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2501.13121","title":"Episodic Memories Generation and Evaluation Benchmark for Large Language Models","created":"2025-01-21","cited_by_count":14,"area":null},{"id":"2602.03085","title":"The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers","created":"2026-02-03","cited_by_count":14,"area":"safety"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2405.08707","title":"Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory","created":"2024-05-14","cited_by_count":12,"area":null},{"id":"2310.15511","title":"KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2406.07735","title":"REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2406.11544","title":"Do Parameters Reveal More than Loss for Membership Inference?","created":"2024-06-17","cited_by_count":10,"area":"safety"},{"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":"2306.01272","title":"DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detection","created":"2023-06-02","cited_by_count":9,"area":"safety"},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","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":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"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":"2412.11044","title":"Understanding and Mitigating Memorization in Diffusion Models for Tabular Data","created":"2024-12-15","cited_by_count":7,"area":"diffusion"},{"id":"2502.03568","title":"Code Simulation as a Proxy for High-order Tasks in Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2502.05087","title":"Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2508.09603","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","created":"2025-08-13","cited_by_count":7,"area":"safety"},{"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":"2510.01454","title":"Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories","created":"2025-10-01","cited_by_count":7,"area":"mllm"},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2408.11546","title":"Memorization in In-Context Learning","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2504.09389","title":"Measuring LLM Novelty As The Frontier Of Original And High-Quality Output","created":"2025-04-13","cited_by_count":6,"area":null},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2603.20957","title":"Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models","created":"2026-03-21","cited_by_count":6,"area":"alignment"},{"id":"2502.13313","title":"Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2503.01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.22948","title":"SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning","created":"2025-03-29","cited_by_count":5,"area":"alignment"},{"id":"2505.20225","title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","created":"2025-05-26","cited_by_count":5,"area":"moe"},{"id":"2508.11551","title":"ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2510.12950","title":"An Investigation of Memorization Risk in Healthcare Foundation Models","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2305.17819","title":"Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2407.07966","title":"A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2410.21750","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","created":"2024-10-29","cited_by_count":4,"area":"safety"},{"id":"2411.07990","title":"Derivational Morphology Reveals Analogical Generalization in Large Language Models","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2412.11302","title":"Sequence-Level Leakage Risk of Training Data in Large Language Models","created":"2024-12-15","cited_by_count":4,"area":null},{"id":"2502.04066","title":"Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training","created":"2025-02-06","cited_by_count":4,"area":null},{"id":"2503.11071","title":"Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models","created":"2025-03-14","cited_by_count":4,"area":"diffusion"},{"id":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2510.16530","title":"Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks","created":"2025-10-18","cited_by_count":4,"area":null}],"next_cursor":"100"}