{"total":80,"rows":[{"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":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"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":"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":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"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":"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":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65,"area":"synth"},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"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":"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":"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":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"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":"2501.12793","title":"Revisit Self-Debugging with Self-Generated Tests for Code Generation","created":"2025-01-22","cited_by_count":22,"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":"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":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16,"area":"synth"},{"id":"2408.02927","title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","created":"2024-08-06","cited_by_count":16,"area":"synth"},{"id":"2311.08921","title":"Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models","created":"2023-11-15","cited_by_count":15,"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":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"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":"2404.12404","title":"EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models","created":"2024-04-15","cited_by_count":14,"area":"synth"},{"id":"2407.12504","title":"Case2Code: Scalable Synthetic Data for Code Generation","created":"2024-07-17","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":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2409.00121","title":"BELT-2: Bootstrapping EEG-to-Language representation alignment for multi-task brain decoding","created":"2024-08-28","cited_by_count":10,"area":"synth"},{"id":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9,"area":"synth"},{"id":"2501.01384","title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","created":"2025-01-02","cited_by_count":9,"area":"synth"},{"id":"2404.14445","title":"A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models","created":"2024-04-20","cited_by_count":8,"area":"synth"},{"id":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","cited_by_count":8,"area":"synth"},{"id":"2410.10864","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","created":"2024-10-07","cited_by_count":8,"area":"synth"},{"id":"2503.12303","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","created":"2025-03-16","cited_by_count":7,"area":"synth"},{"id":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","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":"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":"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":"2409.03381","title":"CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks","created":"2024-09-05","cited_by_count":5,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2502.16280","title":"Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction","created":"2025-02-22","cited_by_count":5,"area":"synth"},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2408.16310","title":"Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning","created":"2024-08-29","cited_by_count":4,"area":"synth"},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","cited_by_count":4,"area":"synth"},{"id":"2502.07164","title":"Does Training on Synthetic Data Make Models Less Robust?","created":"2025-02-11","cited_by_count":3,"area":"synth"},{"id":"2502.18517","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","created":"2025-02-23","cited_by_count":3,"area":"synth"},{"id":"2506.23520","title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","created":"2025-06-30","cited_by_count":3,"area":"synth"},{"id":"2509.15568","title":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","created":"2025-09-19","cited_by_count":3,"area":"synth"},{"id":"2407.03942","title":"Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data","created":"2024-07-04","cited_by_count":2,"area":"synth"},{"id":"2410.12341","title":"Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models","created":"2024-10-16","cited_by_count":2,"area":"synth"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2508.08529","title":"SynLLM: A Comparative Analysis of Large Language Models for Medical Tabular Synthetic Data Generation via Prompt Engineering","created":"2025-08-11","cited_by_count":2,"area":"synth"},{"id":"2510.07189","title":"Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation","created":"2025-10-08","cited_by_count":2,"area":"synth"},{"id":"2605.13369","title":"Query-Conditioned Test-Time Self-Training for Large Language Models","created":"2026-05-13","cited_by_count":2,"area":"synth"},{"id":"2501.07959","title":"Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning","created":"2025-01-14","cited_by_count":1,"area":"synth"},{"id":"2503.13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis","created":"2025-03-18","cited_by_count":1,"area":"synth"},{"id":"2505.06548","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","created":"2025-05-10","cited_by_count":1,"area":"synth"},{"id":"2601.11776","title":"Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models","created":"2026-01-16","cited_by_count":1,"area":"synth"},{"id":"2606.13732","title":"When Sample Selection Bias Precipitates Model Collapse","created":"2026-06-11","cited_by_count":1,"area":"synth"},{"id":"2609.04511","title":"LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs","created":"2026-09-03","cited_by_count":1,"area":"synth"},{"id":"2311.03243","title":"Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM","created":"2023-11-06","cited_by_count":0,"area":"synth"},{"id":"2406.14051","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2505.17671","title":"MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis","created":"2025-05-23","cited_by_count":0,"area":"synth"},{"id":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","cited_by_count":0,"area":"synth"},{"id":"2603.09231","title":"Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2603.16044","title":"Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation","created":"2026-03-17","cited_by_count":0,"area":"synth"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"},{"id":"2608.30619","title":"Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text","created":"2026-08-31","cited_by_count":0,"area":"synth"},{"id":"2609.18878","title":"Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data","created":"2026-09-16","cited_by_count":0,"area":"synth"},{"id":"2609.22149","title":"Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization","created":"2026-08-26","cited_by_count":0,"area":"synth"}],"next_cursor":null}