{"total":14,"rows":[{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2502.04419","title":"Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","created":"2025-02-06","cited_by_count":9,"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":"2503.22006","title":"Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them","created":"2025-03-27","cited_by_count":4,"area":"synth"},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2606.28438","title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","created":"2026-06-26","cited_by_count":2,"area":"synth"},{"id":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2607.17043","title":"Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning","created":"2026-07-19","cited_by_count":1,"area":"synth"},{"id":"2601.03385","title":"SIGMA: Scalable Spectral Insights for LLM Model Collapse","created":"2026-01-06","cited_by_count":0,"area":"synth"},{"id":"2608.04268","title":"The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data","created":"2026-08-04","cited_by_count":0,"area":"synth"},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.01493","title":"No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse","created":"2026-10-01","cited_by_count":0,"area":"synth"}],"next_cursor":null}