{"total":153,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832,"area":"synth"},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207,"area":"synth"},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187,"area":"synth"},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154,"area":"synth"},{"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":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75,"area":"synth"},{"id":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68,"area":"synth"},{"id":"2502.11102","title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","created":"2025-02-16","cited_by_count":49,"area":"synth"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"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":"2305.15035","title":"Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations","created":"2023-05-24","cited_by_count":42,"area":"synth"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","cited_by_count":33,"area":"synth"},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2412.14203","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","created":"2024-12-16","cited_by_count":29,"area":"synth"},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28,"area":"synth"},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"area":"synth"},{"id":"2310.13522","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","created":"2023-10-20","cited_by_count":26,"area":"synth"},{"id":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"area":"synth"},{"id":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","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":"2110.01256","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","created":"2021-10-04","cited_by_count":23,"area":"synth"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"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":"2412.19363","title":"Large Language Models for Market Research: A Data-augmentation Approach","created":"2024-12-26","cited_by_count":20,"area":"synth"},{"id":"2406.10710","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","created":"2024-06-15","cited_by_count":19,"area":"synth"},{"id":"2502.03997","title":"CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing","created":"2025-02-06","cited_by_count":19,"area":"synth"},{"id":"2108.12589","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-08-28","cited_by_count":18,"area":"synth"},{"id":"2402.02285","title":"SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking","created":"2024-02-03","cited_by_count":17,"area":"synth"},{"id":"2410.02064","title":"Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct","created":"2024-10-02","cited_by_count":17,"area":"synth"},{"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":"2506.05109","title":"Truly Self-Improving Agents Require Intrinsic Metacognitive Learning","created":"2025-06-05","cited_by_count":15,"area":"synth"},{"id":"2304.01228","title":"Better Language Models of Code through Self-Improvement","created":"2023-04-02","cited_by_count":14,"area":"synth"},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2307.03692","title":"Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning","created":"2023-07-05","cited_by_count":13,"area":"synth"},{"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":"2411.17672","title":"Synthetic Data Generation with LLM for Improved Depression Prediction","created":"2024-11-26","cited_by_count":13,"area":"synth"},{"id":"2304.11872","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","created":"2023-04-24","cited_by_count":12,"area":"synth"},{"id":"2311.07070","title":"Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations","created":"2023-11-13","cited_by_count":12,"area":"synth"},{"id":"2408.09849","title":"Importance Weighting Can Help Large Language Models Self-Improve","created":"2024-08-19","cited_by_count":12,"area":"synth"},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2505.17231","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","created":"2025-05-22","cited_by_count":12,"area":"synth"},{"id":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","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":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10,"area":"synth"},{"id":"2110.06274","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","created":"2021-10-12","cited_by_count":9,"area":"synth"},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","cited_by_count":9,"area":"synth"},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"area":"synth"},{"id":"2410.24105","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","created":"2024-10-31","cited_by_count":9,"area":"synth"},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","cited_by_count":8,"area":"synth"},{"id":"2504.15573","title":"Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction","created":"2025-04-22","cited_by_count":8,"area":"synth"},{"id":"2404.02422","title":"Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data","created":"2024-04-03","cited_by_count":7,"area":"synth"},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2212.08167","title":"Evaluation of Synthetic Datasets for Conversational Recommender Systems","created":"2022-12-12","cited_by_count":6,"area":"synth"},{"id":"2309.06748","title":"CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation","created":"2023-09-13","cited_by_count":6,"area":"synth"},{"id":"2403.11487","title":"Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis","created":"2024-03-18","cited_by_count":6,"area":"synth"},{"id":"2505.15392","title":"Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations","created":"2025-05-21","cited_by_count":6,"area":"synth"},{"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":"2507.00075","title":"Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap","created":"2025-06-29","cited_by_count":6,"area":"synth"},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2601.21343","title":"Self-Improving Pretraining: using post-trained models to pretrain better models","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"id":"2404.01720","title":"Self-Improvement Programming for Temporal Knowledge Graph Question Answering","created":"2024-04-02","cited_by_count":5,"area":"synth"},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2409.01552","title":"Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs","created":"2024-09-03","cited_by_count":5,"area":"synth"},{"id":"2412.19544","title":"TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data","created":"2024-12-27","cited_by_count":5,"area":"synth"},{"id":"2412.20641","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","created":"2024-12-30","cited_by_count":5,"area":"synth"},{"id":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"area":"synth"},{"id":"2510.16552","title":"LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs","created":"2025-10-18","cited_by_count":5,"area":"synth"},{"id":"2311.02660","title":"LLM-enhanced Self-training for Cross-domain Constituency Parsing","created":"2023-11-05","cited_by_count":4,"area":"synth"},{"id":"2410.15639","title":"Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning","created":"2024-10-21","cited_by_count":4,"area":"synth"},{"id":"2412.00395","title":"On Foundation Models for Dynamical Systems from Purely Synthetic Data","created":"2024-11-30","cited_by_count":4,"area":"synth"},{"id":"2503.02878","title":"Language Models can Self-Improve at State-Value Estimation for Better Search","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2505.00979","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models","created":"2025-05-02","cited_by_count":4,"area":"synth"},{"id":"2506.00649","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction","created":"2025-05-31","cited_by_count":4,"area":"synth"},{"id":"2601.11974","title":"Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement","created":"2026-01-17","cited_by_count":4,"area":"synth"},{"id":"2302.06860","title":"BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction","created":"2023-02-14","cited_by_count":3,"area":"synth"},{"id":"2306.03315","title":"Few Shot Rationale Generation using Self-Training with Dual Teachers","created":"2023-06-05","cited_by_count":3,"area":"synth"},{"id":"2310.01119","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","created":"2023-10-02","cited_by_count":3,"area":"synth"},{"id":"2403.03690","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","created":"2024-03-06","cited_by_count":3,"area":"synth"},{"id":"2405.09997","title":"Generative Design through Quality-Diversity Data Synthesis and Language Models","created":"2024-05-16","cited_by_count":3,"area":"synth"},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","cited_by_count":3,"area":"synth"},{"id":"2503.09029","title":"DAST: Difficulty-Aware Self-Training on Large Language Models","created":"2025-03-12","cited_by_count":3,"area":"synth"},{"id":"2508.09586","title":"EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making","created":"2025-08-13","cited_by_count":3,"area":"synth"},{"id":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"area":"synth"},{"id":"2210.07313","title":"Bootstrapping Multilingual Semantic Parsers using Large Language Models","created":"2022-10-13","cited_by_count":2,"area":"synth"}],"next_cursor":"100"}