# Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation

arXiv: https://arxiv.org/abs/2605.29714 · HTML: https://mlsanity.com/paper/2605.29714/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 26 of 26)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models](https://mlsanity.com/paper/2208.03306/) (2022)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://mlsanity.com/paper/2309.09400/) (2023)
- [Composable Sparse Fine-Tuning for Cross-Lingual Transfer](https://mlsanity.com/paper/2110.07560/) (2021)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [A Closer Look into Mixture-of-Experts in Large Language Models](https://mlsanity.com/paper/2406.18219/) (2024)
- [Learning Language Representations for Typology Prediction](https://mlsanity.com/paper/1707.09569/) (2017)
- [Enhancing Multilingual LLM Pretraining with Model-Based Data Selection](https://mlsanity.com/paper/2502.10361/) (2025)
- [Multilingual Routing in Mixture-of-Experts](https://mlsanity.com/paper/2510.04694/) (2025)
- [Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training](https://mlsanity.com/paper/2212.10503/) (2022)
- [The Hidden Space of Transformer Language Adapters](https://mlsanity.com/paper/2402.13137/) (2024)
- [Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts](https://mlsanity.com/paper/2410.10626/) (2024)
- [Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters](https://mlsanity.com/paper/2407.01406/) (2024)
- [False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models](https://mlsanity.com/paper/2509.18750/) (2025)
- [Revisiting Multilingual Data Mixtures in Language Model Pretraining](https://mlsanity.com/paper/2510.25947/) (2025)

## Built on by (most cited first, 2 of 2)

- [Cross-Lingual Alignment for Decoder-Only Models using MoE Routers](https://mlsanity.com/paper/2610.01921/) (2026)
- [Scaling Laws for Multimodal Data Mixtures](https://mlsanity.com/paper/2610.14423/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this work, we study multilingual routing dynamics during continual pre-training of an English-centric MoE model on a multilingual corpus, analyzing how expert usage varies across languages. We find that continual multilingual pre-training leads to diffused, language-agnostic routing in early and middle layers, with language specialization primarily emerging in the final layers. We also show that token-level vocabulary overlap between languages plays an important role in how languages are routed. Motivated by these findings, we propose a parameter-efficient adaptation strategy that updates language-specific and shared experts in the final MoE layers. Experiments on MultiBLiMP and Belebele show that our method achieves a strong performance-efficiency trade-off, attaining competitive performance relative to fine-tuning complete final layers, while updating less than 2% of the parameters. Overall, our findings provide insights into where and how language specialization emerges in MoEs during continual pre-training and provide practical insights for low-resource multilingual adaptation. Our code is available at https://github.com/aditi184/moe-routing-adaptation.