2026
ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
AAAI 2026technical
Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a LLMs should not know is important for ensuring alignment and thus safe use. However, effective unlearning in LLMs is difficult due to the fuzzy boundary between knowledge retent