AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Multiplicative Orthogonal Sequential Editing for Language Models

Hao-Xiang Xu, Jun-Yu Ma, Ziqi Peng, Yuhao Sun, Zhen-Hua Ling, Jia-Chen Gu

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 1 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 additive update with multiplicative orthogonal update (MOSE vs AlphaEdit)LLaMA3-8B · CounterFact (single-sequential, 4000 edits)Reliability: 0.9018 -> 0.9887Improved
replace additive update with multiplicative orthogonal update (MOSE vs AlphaEdit)LLaMA3-8B · CounterFact (single-sequential, 4000 edits)Locality: 0.7831 -> 0.8972Improved
replace additive update with multiplicative orthogonal update (MOSE vs AlphaEdit)Qwen2.5-7B · CounterFact (single-sequential, 4000 edits)Reliability: 0.9519 -> 0.9981Improved
MOSE vs AlphaEdit on conceptual knowledgeLLaMA3-8B · ConceptEdit-Inter (single-sequential, 4000 edits)Reliability: 0.7012 -> 0.7859Improved
MOSE vs AlphaEdit in batch-sequential editingLLaMA3-8B · CounterFact (batch-sequential, 10x500 edits)Generalization: 0.7835 -> 0.9361Improved
MOSE vs AlphaEdit in batch-sequential editingQwen2.5-7B · CounterFact (batch-sequential, 10x500 edits)Reliability: 0.9427 -> 0.9775Improved
move from single to batch-sequential editing under AlphaEditLLaMA3-8B · CounterFactReliability: 0.9018 -> 0.8222Hurt
add layer selection algorithm over a predefined layer (ablation)MOSE batch-sequential · LLaMA3-8B CounterFactediting performanceImproved
also edit neighboring layers beyond the single selected layer (ablation)MOSE batch-sequential · LLaMA3-8B CounterFactediting performanceImproved
use orthogonal multiplicative update instead of additive update (MOSE vs RECT)sequential editing · CounterFact t-SNE of hidden statesdistribution overlapImproved
MOSE editing time vs AlphaEditMOSE · CounterFacttime per sample (s): 18.53 -> 18.60No clear effect
MOSE editing time vs ROMEMOSE · CounterFacttime per sample (s): 12.09 -> 18.60Hurt

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