AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

Multilingual Routing in Mixture-of-Experts

Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz, Junlin Hu, Nanyun Peng

ICLR 2026 · Architectures and efficiency › Mixture of experts · approach: Efficient MoE language model systems · 19 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
steer router toward English-active math experts in middle layers (soft, lambda 0.5)Qwen3-30B-A3B · MGSM non-English avgaccuracy: 76.4% -> 78.0%Improved
steer router toward English-active math experts in middle layers (soft, lambda 0.5)Phi-3.5-MoE · MGSM non-English avgaccuracy: 57.5% -> 58.9%Improved
force-activate English-active math experts in middle layers (hard)GPT-OSS-20B · MGSM non-English avgaccuracy: 68.9% -> 71.5%Improved
force-activate English-active medicine experts in middle layers (hard)Qwen3-30B-A3B · Global-MMLU Medicine non-English avgaccuracy: 68.2% -> 69.1%Improved
steer toward English-active medicine experts (soft, lambda 0.5)Phi-3.5-MoE · Global-MMLU Medicine non-English avgaccuracy: 57.8% -> 58.8%Improved
steer toward English-active medicine experts (soft, lambda 0.5)GPT-OSS-20B · Global-MMLU Medicine non-English avgaccuracy: 63.8% -> 64.5%Improved
apply steering to low-resource languages only averageGPT-OSS-20B · MGSM low-resource avgaccuracy: 60.0% -> 64.5%Improved
apply steering to English inputPhi-3.5-MoE · MGSM Englishaccuracy: 88.0% -> 85.6%Hurt
deactivate multilingual or task experts in all layers or random subsets (ablation)MoE LLMs · MGSM and Global-MMLUaccuracyHurt
intervene in layers slightly outside the identified middle zone (ablation)MoE LLMs · MGSM and Global-MMLUaccuracyHurt
combine task-expert steering with multilingual-expert activation in top and bottom layers (ablation)MoE LLMs · MGSM and Global-MMLUaccuracyHurt
use larger soft steering strength than 0.5 (ablation)MoE LLMs · MGSM and Global-MMLUaccuracyHurt

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