AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

LLM Unlearning with LLM Beliefs

Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu, Bo Han, Jiantao Zhou

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 10 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 NPO with BS-STOFU unlearning, Llama 3.2 1B · TOFU forget 10%Agg.: 0.58 -> 0.61Improved
replace NPO with BS-TTOFU unlearning, Llama 3.2 1B · TOFU forget 10%Agg.: 0.58 -> 0.59Improved
replace NPO with BS-TTOFU unlearning, Llama 3.1 8B · TOFU forget 10%Agg.: 0.63 -> 0.63No clear effect
replace NPO with BS-STOFU unlearning, Llama 3.2 1B · TOFU forget 1%Agg.: 0.53 -> 0.57Improved
replace NPO with BS-STOFU unlearning, Llama 3.2 3B · TOFU forget 1%Agg.: 0.45 -> 0.50Improved
replace NPO with BS-STOFU unlearning, Llama 3.1 8B · TOFU forget 1%Agg.: 0.44 -> 0.49Improved
replace NPO with BS-STOFU unlearning, Llama 3.1 8B · TOFU forget 5%Agg.: 0.53 -> 0.60Improved
add sequence-level bootstrapping on top of BS-T (BS-S vs BS-T) (ablation)BS-T · TOFU forget 5%, Llama 3.2 3BAgg.: 0.55 -> 0.60Improved
replace WGA with BS-STOFU unlearning, Llama 3.2 1B · TOFU forget 10%Agg.: 0.53 -> 0.61Improved
replace NPO with BS-SZephyr-7B-beta · WMDP BioQA accuracy: 0.27 -> 0.26Improved
replace RMU with BS-SZephyr-7B-beta · MMLU (WMDP retain)accuracy: 0.55 -> 0.54Hurt
replace NPO with BS-SZephyr-7B-beta · MMLU (WMDP retain)accuracy: 0.44 -> 0.54Improved

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