CALIBURN: Self-Calibrated LLM Unlearning Alignment

CALIBURN introduces a self-calibrated alignment method for LLM unlearning that aims to remove undesirable knowledge while preserving model utility.

Recommended citation: Yang, Z., Zhong, Y., Hong, J., & Zhu, Z. (2026). CALIBURN: Self-Calibrated LLM Unlearning Alignment. EMNLP 2026.