Model Collapse in Bangla and English: A Pre-Registered Study of Iterative Self-Training with Gemma-3-270m
Pre-registration of a computational experiment on model collapse in a low-resource language setting, frozen before any model is trained. We fine-tune the open-weight model google/gemma-3-270m (bfloat16) in Bangla and in English over six generations of self-training, where each generation is trained on text generated by...