Ruben Nuredini

When Medical LLMs Eat Their Own Output: The Effects of Recursive Self-Training on German Medical Text

This work investigates the impact of recursive self-training on German-language medical text by recursively fine-tuning a medically specialized language model over multiple iterations and suggests that human-anchored recursive training (blending synthetic data with real, human-generated data) constitutes a promising mitigation strategy against recursive degradation.