Hong, I., Yu, C., Xu, Z., Liu, X., Zhang, Y., Lu, Q., Yin, B., & Zhao, T. (2026). Training LLM Judges from Language Feedback via Position-Selective Self-Distillation. https://omanscience.com/en/articles/training-llm-judges-from-language-feedback-via-position-selective-self-distillation