AI Paper Atlas

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

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

Yujie Lin, Chengyi Yang, Zhishang Xiang, YIPING SONG, Jinsong Su

ICML 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 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
use ZeroUnlearn instead of AlphaEditLlama-3.1 · MCF few-shotefficacy (Eff.): 0.20 -> 0.00Improved
use ZeroUnlearn instead of AlphaEditLlama-3.2 · MCF few-shotefficacy (Eff.): 2.60 -> 0.40Improved
use ZeroUnlearn instead of AlphaEditLlama-3.2 · MCF few-shotgeneralization (Gen.): 11.80 -> 4.60Improved
use ZeroUnlearn instead of AlphaEditLlama-3.2 · MCF few-shotspecificity (Spe.): 18.36 -> 14.90Hurt
use ZeroUnlearn instead of AlphaEditLlama-3.2 · ZsRE few-shotefficacy (Eff.): 29.59 -> 27.85Improved
use ZeroUnlearn instead of GALlama-3.2 · MCF few-shotPPL: >1000 -> 13.06Improved
use ZeroUnlearn instead of FTLlama-3.2 · MCF few-shotspecificity (Spe.): 0.00 -> 14.90Improved
use ZeroUnlearn instead of ROMELlama-3.1 · MCF few-shotefficacy (Eff.): 24.40 -> 0.00Improved
use ZeroUnlearn instead of MEMITLlama-3.1 · MCF few-shotefficacy (Eff.): 9.60 -> 0.00Improved
use ZeroUnlearn-GD instead of AlphaEdit for 1000-sample unlearningLlama-3.2 · MCF multiple unlearningefficacy (Eff.): 1.40 -> 0.00Improved
use ZeroUnlearn-GD instead of AlphaEdit for 1000-sample unlearningLlama-3.2 · MCF multiple unlearningspecificity (Spe.): 15.68 -> 12.41Hurt
use ZeroUnlearn-GD instead of AlphaEdit for 1000-sample unlearningLlama-3.2 · ZsRE multiple unlearningefficacy (Eff.): 27.66 -> 25.29Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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