AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

OnEDIT: Online Editing with Decoupled Implicit Task for Large Language Models

Chae-Won Lee, Jae-Hong Lee, Ji-Hun Kang, Joon-Hyuk Chang

AAAI 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Continual pretraining of language models · 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 OnEDIT instead of GainLoRAT5-large · Long Sequence benchmarkAP: 29.8 -> 38.4Improved
use OnEDIT instead of GainLoRAT5-large · Standard CIT benchmarkAP: 66.4 -> 67.4Improved
use OnEDIT instead of GainLoRAT5-large · SuperNI benchmarkAP: 27.6 -> 28.9Improved
use OnEDIT instead of GainLoRAT5-large · Standard CIT benchmarkforgetting rate: 24.8 -> 22.3Improved
use OnEDIT instead of GainLoRAT5-large · SuperNI benchmarkforgetting rate: 12.3 -> 15.4Hurt
use OnEDIT instead of plain LoRAT5-large · Long Sequence benchmarkAP: 17.8 -> 38.4Improved
use OnEDIT instead of GainLoRALlama3-8B · Standard CIT benchmarkAP: 67.4 -> 69.6Improved
use OnEDIT instead of GainLoRALlama3-8B-chat · Standard CIT benchmarkAP: 67.8 -> 69.5Improved
use OnEDIT instead of GainLoRALlama3-8B · Standard CIT benchmarkforgetting rate: 25.2 -> 20.5Improved
use OnEDIT instead of OLoRAT5-large · Standard CIT benchmarkAP: 60.1 -> 67.4Improved
use OnEDIT instead of OLoRA for efficiencyT5-large · adaptation timetime (s): 101.6 -> 42.2Improved
use OnEDIT instead of LoRA for efficiencyT5-large · adaptation timetime (s): 39.7 -> 42.2Hurt

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