{"total":356,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"area":"lr"},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"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":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143,"area":"lr"},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"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":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119,"area":"alignment"},{"id":"2404.01268","title":"Mapping the Increasing Use of LLMs in Scientific Papers","created":"2024-04-01","cited_by_count":118,"area":null},{"id":"2306.07899","title":"Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks","created":"2023-06-13","cited_by_count":103,"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":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"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":"2407.03502","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","created":"2024-07-03","cited_by_count":89,"area":"agents"},{"id":"2311.04378","title":"Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models","created":"2023-11-07","cited_by_count":87,"area":"safety"},{"id":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84,"area":null},{"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":"2402.19450","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","created":"2024-02-29","cited_by_count":79,"area":"lr"},{"id":"2404.05090","title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse","created":"2024-04-07","cited_by_count":79,"area":"synth"},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2403.14117","title":"A Design Space for Intelligent and Interactive Writing Assistants","created":"2024-03-21","cited_by_count":76,"area":null},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"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":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65,"area":"synth"},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2403.07857","title":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","created":"2024-03-12","cited_by_count":55,"area":null},{"id":"2306.06130","title":"Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet","created":"2023-06-08","cited_by_count":54,"area":null},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53,"area":"lr"},{"id":"2401.12970","title":"Raidar: geneRative AI Detection viA Rewriting","created":"2024-01-23","cited_by_count":52,"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":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43,"area":"synth"},{"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":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2308.13565","title":"DARWIN Series: Domain Specific Large Language Models for Natural Science","created":"2023-08-25","cited_by_count":39,"area":null},{"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":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","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":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"id":"2307.02192","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","created":"2023-07-05","cited_by_count":34,"area":null},{"id":"2404.03502","title":"AI and the Problem of Knowledge Collapse","created":"2024-04-04","cited_by_count":34,"area":null},{"id":"2310.11158","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","created":"2023-10-17","cited_by_count":33,"area":null},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2411.18810","title":"All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds","created":"2024-11-27","cited_by_count":31,"area":"diffusion"},{"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":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31,"area":null},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2306.13384","title":"DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology","created":"2023-06-23","cited_by_count":29,"area":"diffusion"},{"id":"2402.11778","title":"Towards Theoretical Understandings of Self-Consuming Generative Models","created":"2024-02-19","cited_by_count":29,"area":null},{"id":"2406.14517","title":"PostMark: A Robust Blackbox Watermark for Large Language Models","created":"2024-06-20","cited_by_count":29,"area":"safety"},{"id":"2306.13723","title":"Human-AI Coevolution","created":"2023-06-23","cited_by_count":27,"area":null},{"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":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2412.17646","title":"Rate of Model Collapse in Recursive Training","created":"2024-12-23","cited_by_count":25,"area":"synth"},{"id":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"area":"synth"},{"id":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"area":null},{"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":"2401.13481","title":"How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment","created":"2024-01-24","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":"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":"2405.01820","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"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":"2401.06883","title":"Scaling While Privacy Preserving: A Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics","created":"2024-01-12","cited_by_count":19,"area":null},{"id":"2406.01860","title":"Eliciting the Priors of Large Language Models using Iterated In-Context Learning","created":"2024-06-04","cited_by_count":19,"area":null},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2307.02599","title":"Evade ChatGPT Detectors via A Single Space","created":"2023-07-05","cited_by_count":18,"area":null},{"id":"2311.09402","title":"Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research","created":"2023-11-15","cited_by_count":18,"area":"diffusion"},{"id":"2403.07750","title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings","created":"2024-03-12","cited_by_count":18,"area":"mllm"},{"id":"2407.04503","title":"When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2310.15296","title":"DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM","created":"2023-10-23","cited_by_count":16,"area":"diffusion"},{"id":"2405.04219","title":"Iterative Experience Refinement of Software-Developing Agents","created":"2024-05-07","cited_by_count":16,"area":"agents"},{"id":"2405.19266","title":"PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications","created":"2024-05-29","cited_by_count":16,"area":null},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16,"area":"lr"},{"id":"2404.12691","title":"Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?","created":"2024-04-19","cited_by_count":15,"area":null}],"next_cursor":"100"}