AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs

Xunlei Chen, Jinyu Guo, Yuang Li, Zhaokun Wang, Yi Gong, Jie Zou, Jiwei Wei, Wenhong Tian

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace single LoRA with asymmetric LoRA (shared A, separate B experts) (ablation)LoRA unlearning · WMDP-Bio / MMLU (Llama3-8B)MMLU accuracy (%): 39.6 -> 55.3Improved
add token-entropy-guided routing and Tsallis-entropy loss on top of AsymLoRA (ablation)AsymLoRA · WMDP-Cyber (Llama3-8B)accuracy (%): 28.8 -> 25.6Improved
add token-entropy guidance on top of AsymLoRA (ablation)AsymLoRA · WMDP fluency (Llama3-8B)Flu-mean: 2.23 -> 3.46Improved
add token-entropy guidance on top of AsymLoRA (ablation)AsymLoRA · MMLU after WMDP unlearning (Llama3-8B)accuracy (%): 55.3 -> 57.8Improved
ALTER vs gradient ascent / random label baselinesunlearning methods · MMLU after WMDP unlearning (Llama3-8B)accuracy (%): 24.8 -> 57.8Improved
ALTER vs RMUunlearning methods · WMDP-Bio (Llama3-8B)accuracy (%): 49.4 -> 24.4Improved
apply ALTER for unlearning Harry Potter (ablation)Llama-2-7B · Harry Potter (MUSE)MMLU: 38.9 (LoRA) -> 44.6Improved
ALTER vs KL minimization on forget metricunlearning methods · Harry Potter (MUSE)ASG: 0.8 (KL) vs 1.3 (ALTER)No clear effect
use AsymLoRA framework instead of full-parameter baselinesunlearning · TOFU-10% (Llama2-7B)training time: time cost reduced by 86.1% to 87.1%Improved
add token-entropy guidance to AsymLoRA (ablation)AsymLoRA · TOFU-10% (Llama2-7B)training time: 1.0 -> 1.25xHurt
use ALTER in sequential unlearning roundsLlama3-8B on TOFU · TOFU sequential unlearning 1% to 10%model utilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy