AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Massive Editing for Large Language Models Based on Dynamic Weight Generation

Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 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 InfoNCE contrastive fine-tuning of the text encoder instead of frozen BERT (ablation)MeG · CounterFact GPT-J 1024 editsGenerality AG: 18.46 -> 84.96Improved
use InfoNCE instead of MSE fine-tuning of the text encoder (ablation)MeG · CounterFact GPT-J 1024 editsGenerality AG: 56.54 -> 84.96Improved
add the Familiarity Network (ablation)MeG · ZsRE Phi-2 1024 editsScore: 81.32 -> 91.30Improved
add the Familiarity Network (ablation)MeG · ZsRE Phi-2 1024 editsLocality AG: 53.81 -> 88.67Improved
add the Familiarity Network (ablation)MeG · ZsRE Phi-2 1024 editsGenerality AG: 83.50 -> 80.37Hurt
use DiT instead of MLP weight generator (ablation)MeG · ZsRE Llama-3 10000 editsScore: 76.21 -> 83.90Improved
use DiT instead of MLP weight generator (ablation)MeG · ZsRE Llama-3 10000 editsGenerality AG: 45.49 -> 61.33Improved
use DiT instead of MLP weight generator (ablation)MeG · ZsRE Llama-3 1024 editsLocality AG: 81.64 -> 78.71Hurt
reduce diffusion steps from 1000 to 50 (ablation)MeG · ZsRE Phi-2 10000 editsScore: 82.80 -> 82.51No clear effect
reduce diffusion steps from 1000 to 10 (ablation)MeG · ZsRE Phi-2 10000 editsScore: 82.80 -> 77.83Hurt
reduce diffusion steps from 1000 to 50 (inference cost) (ablation)MeG · ZsRE Phi-2 10000 editsdiffusion time per edit (s): 0.304 -> 0.031Improved
increase edit count from 1024 to 10000 (ablation)MeG w/o Familiarity Network · ZsRE Phi-2Score: 81.32 -> 73.09Hurt

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