{"total":220,"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":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670,"area":null},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2212.03860","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","created":"2022-12-07","cited_by_count":424,"area":"diffusion"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"area":"safety"},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195,"area":"rag"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178,"area":null},{"id":"2305.14552","title":"Sources of Hallucination by Large Language Models on Inference Tasks","created":"2023-05-23","cited_by_count":169,"area":null},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150,"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":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"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":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"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":"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":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2302.10870","title":"On Provable Copyright Protection for Generative Models","created":"2023-02-21","cited_by_count":98,"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":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"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":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"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":"2506.12618","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","created":"2025-06-14","cited_by_count":83,"area":"safety"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65,"area":null},{"id":"2302.05981","title":"MarioGPT: Open-Ended Text2Level Generation through Large Language Models","created":"2023-02-12","cited_by_count":64,"area":null},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2305.19555","title":"Large Language Models Are Not Strong Abstract Reasoners","created":"2023-05-31","cited_by_count":53,"area":"lr"},{"id":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"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":"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":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2307.04401","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","created":"2023-07-10","cited_by_count":36,"area":null},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2308.15419","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","created":"2023-08-29","cited_by_count":35,"area":null},{"id":"2405.13001","title":"Large Language Models for Education: A Survey","created":"2024-05-12","cited_by_count":34,"area":null},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2309.17322","title":"Assessing Look-Ahead Bias in Stock Return Predictions Generated By GPT Sentiment Analysis","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2307.10558","title":"Instruction-following Evaluation through Verbalizer Manipulation","created":"2023-07-20","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":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27,"area":"safety"},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2406.08689","title":"Security of AI Agents","created":"2024-06-12","cited_by_count":26,"area":"agents"},{"id":"2310.13061","title":"To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets","created":"2023-10-19","cited_by_count":24,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"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":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2403.06644","title":"Elephants Never Forget: Testing Language Models for Memorization of Tabular Data","created":"2024-03-11","cited_by_count":19,"area":null},{"id":"2305.09144","title":"Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models","created":"2023-05-16","cited_by_count":18,"area":null},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18,"area":null},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2311.14740","title":"AutoKG: Efficient Automated Knowledge Graph Generation for Language Models","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"area":"safety"},{"id":"2402.02987","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","created":"2024-02-05","cited_by_count":16,"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":"2309.05217","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","created":"2023-09-11","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2409.03659","title":"LLM-based multi-agent poetry generation in non-cooperative environments","created":"2024-09-05","cited_by_count":15,"area":"agents"},{"id":"2304.03816","title":"Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions","created":"2023-04-07","cited_by_count":14,"area":null},{"id":"2404.08417","title":"AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees","created":"2024-04-12","cited_by_count":14,"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":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2406.14318","title":"The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2407.05365","title":"ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models","created":"2024-07-07","cited_by_count":13,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2210.12929","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"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":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2408.05131","title":"Range Membership Inference Attacks","created":"2024-08-09","cited_by_count":12,"area":"safety"},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2307.00310","title":"Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD","created":"2023-07-01","cited_by_count":11,"area":null},{"id":"2405.04912","title":"GP-MoLFormer: A Foundation Model For Molecular Generation","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","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":"2510.05141","title":"To model human linguistic prediction, make LLMs less superhuman","created":"2025-10-01","cited_by_count":11,"area":null},{"id":"2510.19796","title":"Blackbox Model Provenance via Palimpsestic Membership Inference","created":"2025-10-22","cited_by_count":11,"area":"safety"}],"next_cursor":"100"}