AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts

Jiajun Liu, Yao He, Wenjun Ke, Peng Wang, Ziyu Shang, Guozheng Li, Zijie Xu

AAAI 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 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 Monte Carlo expert exploration (ablation)B-Distill · General benchmarks avg (Llama3.2-1B-MoE)Rouge-L: 22.80 -> 23.76Improved
add Monte Carlo expert exploration (ablation)B-Distill · General benchmarks avg (Qwen3-0.6B-MoE)Rouge-L: 12.96 -> 16.37Improved
add entropy-aware router distillation (ablation)B-Distill · General benchmarks avg (Llama3.2-1B-MoE)Rouge-L: 22.37 -> 23.76Improved
add entropy-aware router distillation (ablation)B-Distill · General benchmarks avg (Qwen3-0.6B-MoE)Rouge-L: 10.35 -> 16.37Improved
use B-Distill moe-to-moe instead of best dense-to-dense baselineLlama3.2-1B-MoE · general avg Rouge-LRouge-L: 22.32 -> 23.76Improved
use B-Distill instead of best baselineQwen3-0.6B-MoE · medical/legal MMLU avgaccuracy: 0.42 -> 0.46Improved
increase exploration length K from 3 to above 3 (ablation)B-Distill · general benchmarks Rouge-LRouge-LHurt
raise entropy weight beta from 0 to 0.1 (ablation)B-Distill · general benchmarks avgRouge-L: 14.5 -> 16.0 (Llama), 21.5 -> 23.3 (Qwen)Improved
raise entropy weight beta from 0.1 to 0.4 (ablation)B-Distill · general benchmarks avgRouge-L: within 0.4No clear effect
use 4->4 experts instead of 4->1 (moe-to-dense) in student (ablation)B-Distill · general benchmarks avgRouge-L: 20.9 -> 23.8 (Llama); 12.4 -> 15.6 (Qwen)Improved

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