AI Paper Atlas

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

EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning

Jing-Cheng Pang, Sun Liu, Chang Zhou, Xian Tang, Haichuan Ma, KUN JIANG, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai, Chenwei Wu, Xubin Li and 1 more

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning · 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 entropy-based dynamic curriculum instead of random samplingQwen3-4B RLFT · Datacomaccuracy: 40.43 -> 46.96Improved
use EDCO instead of static curricula (RS, AC) in Wireless RLFTQwen3-4B RLFT · Wirelessaccuracy: 34.35 (RS) -> 38.70Improved
use static easy-to-hard curricula (Length, AC, PPL) instead of random sampling in SFTQwen3-4B SFT · WirelessaccuracyHurt
use EDCO in SFT instead of PPL curriculumQwen3-4B SFT · Wireless and Datacomaccuracy: +2.0% (Wireless), +3.3% (Datacom) over PPLImproved
use EDCO instead of baselines on medical RLFTLlama3.2-3B RLFT · MedQAaccuracy: 32.9 (RS) -> 36.7Improved
replace selection signal from inference entropy to perplexity (Dynamic-PPL) (ablation)EDCO · Datacom (Qwen3-4B)accuracy: 41.3 -> 47.0Improved
use heuristic dynamic update without learnable bandit policy (EDCO vs SEC)curriculum selection · Datacom (Qwen3-4B)accuracy: 34.78 -> 47.0Improved
select highest-entropy samples instead of a moderate-entropy window (ablation)EDCO · Datacom (Qwen3-4B)accuracy: 44.78 -> 46.96Improved
use prefix entropy approximation instead of full-sequence entropy (ablation)EDCO entropy estimator · entropy estimation costseconds per sample: 2.24 -> 0.37Improved
increase prefix length from 20 to 128 tokens (ablation)EDCO · Datacom (Qwen3-4B)accuracy: 43.91 -> 46.96Improved
add quick-answer prompting to prefix entropy (ablation)EDCO entropy estimator · rank alignment of prefix and full-sequence entropyrank correlationImproved
increase curriculum size N from 200 to 600 (ablation)EDCO · final scorefinal score: 0.801 -> 0.817Improved

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