Chen, X., Guo, J., Li, Y., Wang, Z., Gong, Y., Zou, J., … Tian, W. (2026). ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(42), 35366–35374. https://doi.org/10.1609/aaai.v40i42.40845