{"total":250,"rows":[{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"area":"lr"},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151,"area":"synth"},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2402.06121","title":"Iterated Denoising Energy Matching for Sampling from Boltzmann Densities","created":"2024-02-09","cited_by_count":116,"area":null},{"id":"2310.14724","title":"A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions","created":"2023-10-23","cited_by_count":105,"area":null},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100,"area":null},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","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":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2406.09358","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","created":"2024-06-13","cited_by_count":91,"area":"diffusion"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79,"area":null},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65,"area":"synth"},{"id":"2403.07857","title":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","created":"2024-03-12","cited_by_count":55,"area":null},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39,"area":"lr"},{"id":"2310.20501","title":"Neural Retrievers are Biased Towards LLM-Generated Content","created":"2023-10-31","cited_by_count":38,"area":null},{"id":"2410.23746","title":"DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios","created":"2024-10-31","cited_by_count":38,"area":null},{"id":"2402.07087","title":"Self-Correcting Self-Consuming Loops for Generative Model Training","created":"2024-02-11","cited_by_count":37,"area":null},{"id":"2408.16333","title":"Self-Improving Diffusion Models with Synthetic Data","created":"2024-08-29","cited_by_count":35,"area":"diffusion"},{"id":"2401.05033","title":"Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk","created":"2024-01-10","cited_by_count":34,"area":"agents"},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31,"area":"synth"},{"id":"2402.11778","title":"Towards Theoretical Understandings of Self-Consuming Generative Models","created":"2024-02-19","cited_by_count":29,"area":null},{"id":"2407.10910","title":"DataDream: Few-shot Guided Dataset Generation","created":"2024-07-15","cited_by_count":29,"area":"diffusion"},{"id":"2311.12202","title":"Nepotistically Trained Generative-AI Models Collapse","created":"2023-11-20","cited_by_count":27,"area":null},{"id":"2410.22812","title":"Universality of the $\\pi^2/6$ Pathway in Avoiding Model Collapse","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2412.17646","title":"Rate of Model Collapse in Recursive Training","created":"2024-12-23","cited_by_count":25,"area":"synth"},{"id":"2307.07367","title":"Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow","created":"2023-07-14","cited_by_count":22,"area":null},{"id":"2404.02325","title":"Heat Death of Generative Models in Closed-Loop Learning","created":"2024-04-02","cited_by_count":22,"area":"diffusion"},{"id":"2411.16171","title":"Image Generation Diversity Issues and How to Tame Them","created":"2024-11-25","cited_by_count":22,"area":"diffusion"},{"id":"2402.03214","title":"Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?","created":"2024-02-05","cited_by_count":21,"area":null},{"id":"2407.02446","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling","created":"2024-07-02","cited_by_count":20,"area":"wm"},{"id":"2410.10437","title":"Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models","created":"2024-10-14","cited_by_count":20,"area":"diffusion"},{"id":"2412.02674","title":"Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models","created":"2024-12-03","cited_by_count":18,"area":"synth"},{"id":"2506.10038","title":"Ambient Diffusion Omni: Training Good Models with Bad Data","created":"2025-06-10","cited_by_count":18,"area":"diffusion"},{"id":"2509.16499","title":"A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective","created":"2025-09-20","cited_by_count":18,"area":"diffusion"},{"id":"2502.18865","title":"A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops","created":"2025-02-26","cited_by_count":16,"area":"synth"},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2407.12835","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","created":"2024-07-03","cited_by_count":15,"area":"synth"},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15,"area":null},{"id":"2402.07610","title":"Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping","created":"2024-02-12","cited_by_count":14,"area":"synth"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2311.09214","title":"Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models","created":"2023-11-15","cited_by_count":13,"area":"lr"},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","cited_by_count":13,"area":"synth"},{"id":"2505.19046","title":"When Models Don't Collapse: On the Consistency of Iterative MLE","created":"2025-05-25","cited_by_count":13,"area":"synth"},{"id":"2404.08254","title":"Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models","created":"2024-04-12","cited_by_count":12,"area":"diffusion"},{"id":"2407.17493","title":"Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling","created":"2024-07-04","cited_by_count":12,"area":"synth"},{"id":"2410.15234","title":"Bias Amplification: Large Language Models as Increasingly Biased Media","created":"2024-10-19","cited_by_count":12,"area":"synth"},{"id":"2505.12108","title":"EarthSynth: Generating Informative Earth Observation with Diffusion Models","created":"2025-05-17","cited_by_count":12,"area":"diffusion"},{"id":"2412.08175","title":"Analyzing and Mitigating Model Collapse in Rectified Flow Models","created":"2024-12-11","cited_by_count":11,"area":"diffusion"},{"id":"2502.08924","title":"Escaping Collapse: The Strength of Weak Data for Large Language Model Training","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2410.14677","title":"Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2502.18049","title":"Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework","created":"2025-02-25","cited_by_count":10,"area":"synth"},{"id":"2504.08755","title":"Delving into: the quantification of Ai-generated content on the internet (synthetic data)","created":"2025-03-29","cited_by_count":10,"area":"synth"},{"id":"2505.09768","title":"Self-Consuming Generative Models with Adversarially Curated Data","created":"2025-05-14","cited_by_count":10,"area":null},{"id":"2509.01620","title":"Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2406.03720","title":"JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits","created":"2024-06-06","cited_by_count":9,"area":"diffusion"},{"id":"2412.20704","title":"HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images","created":"2024-12-30","cited_by_count":9,"area":"diffusion"},{"id":"2509.22341","title":"Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression","created":"2025-09-26","cited_by_count":9,"area":"synth"},{"id":"2309.05940","title":"Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking","created":"2023-09-12","cited_by_count":8,"area":"safety"},{"id":"2412.11385","title":"Why Does ChatGPT \"Delve\" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"alignment"},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2403.10424","title":"Structured Evaluation of Synthetic Tabular Data","created":"2024-03-15","cited_by_count":7,"area":null},{"id":"2407.18421","title":"Self-Directed Synthetic Dialogues and Revisions Technical Report","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2410.08942","title":"Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2507.04219","title":"Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs","created":"2025-07-06","cited_by_count":7,"area":"synth"},{"id":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","cited_by_count":7,"area":"synth"},{"id":"2512.05145","title":"Self-Improving VLM Judges Without Human Annotations","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2312.13480","title":"InvertibleNetworks.jl: A Julia package for scalable normalizing flows","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2502.04468","title":"Iterative Importance Fine-tuning of Diffusion Models","created":"2025-02-06","cited_by_count":6,"area":"diffusion"},{"id":"2505.21677","title":"What happens when generative AI models train recursively on each others' outputs?","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.07459","title":"ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning","created":"2025-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2506.15690","title":"LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs","created":"2025-05-26","cited_by_count":6,"area":"synth"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2604.26965","title":"The Impact of AI-Generated Text on the Internet","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2404.10496","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","created":"2024-04-16","cited_by_count":5,"area":"rag"},{"id":"2405.17998","title":"Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2405.18029","title":"Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?","created":"2024-05-28","cited_by_count":5,"area":"diffusion"},{"id":"2505.08803","title":"Multi-modal Synthetic Data Training and Model Collapse: Insights from VLMs and Diffusion Models","created":"2025-05-10","cited_by_count":5,"area":"diffusion"},{"id":"2506.21209","title":"BitMark: Watermarking Bitwise Autoregressive Image Generative Models","created":"2025-06-26","cited_by_count":5,"area":"safety"},{"id":"2510.03597","title":"Neon: Negative Extrapolation From Self-Training Improves Image Generation","created":"2025-10-04","cited_by_count":5,"area":null}],"next_cursor":"100"}