{"total":50,"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":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349,"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":"2305.14483","title":"Language Model Self-improvement by Reinforcement Learning Contemplation","created":"2023-05-23","cited_by_count":75,"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":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36,"area":"synth"},{"id":"2412.06176","title":"AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement","created":"2024-12-09","cited_by_count":35,"area":"synth"},{"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":"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":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"area":"synth"},{"id":"2503.00735","title":"LADDER: Self-Improving LLMs Through Recursive Problem Decomposition","created":"2025-03-02","cited_by_count":25,"area":"synth"},{"id":"2312.08303","title":"Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models","created":"2023-12-13","cited_by_count":21,"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":"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":"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":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","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":"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":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"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":"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":"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":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2601.21464","title":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"id":"2410.02992","title":"Learning to Better Search with Language Models via Guided Reinforced Self-Training","created":"2024-10-03","cited_by_count":5,"area":"synth"},{"id":"2509.25672","title":"SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation","created":"2025-09-30","cited_by_count":5,"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":"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":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","cited_by_count":3,"area":"synth"},{"id":"2506.19082","title":"FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation","created":"2025-06-23","cited_by_count":3,"area":"synth"},{"id":"2509.23002","title":"Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty","created":"2025-09-26","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":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"area":"synth"},{"id":"2405.19773","title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","created":"2024-05-30","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":"2604.16322","title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","created":"2026-02-27","cited_by_count":1,"area":"synth"},{"id":"2606.21631","title":"CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-Training","created":"2026-06-19","cited_by_count":1,"area":"synth"},{"id":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2407.11017","title":"Direct-Inverse Prompting: Analyzing LLMs' Discriminative Capacity in Self-Improving Generation","created":"2024-06-27","cited_by_count":0,"area":"synth"},{"id":"2509.26340","title":"Memory-Driven Self-Improvement for Decision Making with Large Language Models","created":"2025-09-30","cited_by_count":0,"area":"synth"},{"id":"2510.18257","title":"DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization","created":"2025-10-21","cited_by_count":0,"area":"synth"},{"id":"2511.01183","title":"QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code","created":"2025-11-03","cited_by_count":0,"area":"synth"},{"id":"2601.00885","title":"Counterfactual Self-Questioning for Stable Policy Optimization in Language Models","created":"2025-12-31","cited_by_count":0,"area":"synth"},{"id":"2601.09734","title":"From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis","created":"2025-12-31","cited_by_count":0,"area":"synth"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2609.36750","title":"Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving","created":"2026-09-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}