AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models

Xuyang Zhong, Qizhang Li, Steven Y. Guo, Chen Liu

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Continual pretraining of language models · 0 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
add shared base state with decoupled delta statesDualOptim · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 57.96 -> 59.57Improved
add shared base state with decoupled delta statesDualOptim · Real-world unlearning ME+GD (Llama-3-8B)OVR: 67.60 -> 73.13Improved
add shared base state with decoupled delta statesDualOptim · Real-world unlearning IDK+GD (Llama-3-8B)OVR: 52.73 -> 52.90Mixed
add shared base state with decoupled delta statesDualOptim 8bit · Multi-task learning (Llama-2-7B)average accuracy: 64.36 -> 67.14Improved
use alternating updates instead of joint updateJoint · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 50.85 -> 56.91Improved
update base state after parameter update instead of before delta (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 58.93 -> 59.57Improved
update base state after parameter update instead of after delta (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 58.14 -> 59.57Improved
update base state with raw gradient instead of g minus delta (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 59.08 -> 59.57Improved
use fast momentum for both states instead of slow for both (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 57.59 -> 59.57Improved
use fast momentum for base state instead of slow (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 58.88 -> 59.57Improved
quantize base and delta states to 8 bit (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 59.57 -> 58.55Hurt
set retain frequency Fr=5 instead of 1 (ablation)DualOptim+ · TOFU forget 5% IDK+GD (Phi-1.5)OVR: 59.13 -> 61.30Improved

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