AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Fine-tuning Done Right in Model Editing

Wanli Yang, Rui Tang, Hongyu Zang, Du Su, Qi Cao, Jingang Wang, Huawei Shen, Xueqi Cheng, Fei Sun

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems

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
switch from depth-first to breadth-first pipeline (ablation)FT-M · ZsRE, LLaMA3-8Breliability: 75.30 -> 99.70Improved
switch from depth-first to breadth-first pipeline (ablation)AdaLoRA · ZsRE, LLaMA3-8Breliability: 3.80 -> 90.50Improved
switch from depth-first to breadth-first pipeline (ablation)FT-L · ZsRE, LLaMA3-8Breliability: 0.00 -> 0.00No clear effect
switch from depth-first to breadth-first pipeline (ablation)RoseLoRA · ZsRE, LLaMA3-8Breliability: 0.30 -> 1.00No clear effect
use mini-batch updates instead of batch size 1 in breadth-first pipeline (ablation)FT-M · ZsREcapabilityImproved
use larger batch sizes in breadth-first pipeline (ablation)FT-M and AdaLoRA · ZsREgeneralizationHurt
tune MLP down-projection in later layers instead of coarser modules (ablation)LocFT-BF · ZsRE, 1000 editscapabilityImproved
tune coarser modules (entire layer, full MLP) instead of MLP up/down (ablation)fine-tuning editing · ZsRE, 1000 editsgeneralizationImproved
add prefix-based data augmentation (5 random prefixes) (ablation)LocFT-BF · CounterFact, LLaMA3-8Bgeneralization: 33.23 -> 50.93Improved
use proportional layer position instead of default position (ablation)LocFT-BF · ZsRE, Qwen2.5-32Bcapability: 60.27 -> 64.72Improved
use full-parameter fine-tuning instead of localized tuning (ablation)LocFT-BF · ZsRE, LLaMA3-8B (LlamaFactory)capability: 56.03 -> 40.44Hurt
apply LocFT-BF in place of RLEdit and UltraEdit when scaling to larger modelsLocFT-BF · ZsRE, Qwen2.5-14Breliability: 8.90 -> 99.00Improved

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