# THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation

arXiv: https://arxiv.org/abs/2505.14173 · HTML: https://mlsanity.com/paper/2505.14173/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models](https://mlsanity.com/paper/2208.03306/) (2022)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [O1 Replication Journey: A Strategic Progress Report -- Part 1](https://mlsanity.com/paper/2410.18982/) (2024)
- [DEMix Layers: Disentangling Domains for Modular Language Modeling](https://mlsanity.com/paper/2108.05036/) (2021)
- [Taming Sparsely Activated Transformer with Stochastic Experts](https://mlsanity.com/paper/2110.04260/) (2021)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models](https://mlsanity.com/paper/2404.10237/) (2024)
- [AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models](https://mlsanity.com/paper/2406.13233/) (2024)
- [Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free](https://mlsanity.com/paper/2410.10814/) (2024)
- [Improving Multilingual Translation by Representation and Gradient Regularization](https://mlsanity.com/paper/2109.04778/) (2021)
- [HMoE: Heterogeneous Mixture of Experts for Language Modeling](https://mlsanity.com/paper/2408.10681/) (2024)
- [HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts](https://mlsanity.com/paper/2402.12656/) (2024)
- [Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation](https://mlsanity.com/paper/2011.00678/) (2020)
- [Learning Language-Specific Layers for Multilingual Machine Translation](https://mlsanity.com/paper/2305.02665/) (2023)
- [Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation](https://mlsanity.com/paper/2212.07571/) (2022)
- [Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions](https://mlsanity.com/paper/2211.01542/) (2022)

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

- [Mtextsuperscript4Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation](https://mlsanity.com/paper/2605.02444/) (2026)
- [MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2607.24030/) (2026)

## Abstract (arXiv)

The sparse Mixture-of-Experts (MoE) has achieved significant progress for neural machine translation (NMT). However, there exist two limitations in current MoE solutions which may lead to sub-optimal performance: 1) they directly use the task knowledge of NMT into MoE (e.g., domain/linguistics-specific knowledge), which are generally unavailable at practical application and neglect the naturally grouped domain/linguistic properties; 2) the expert selection only depends on the localized token representation without considering the context, which fully grasps the state of each token in a global view. To address the above limitations, we propose THOR-MoE via arming the MoE with hierarchical task-guided and context-responsive routing policies. Specifically, it 1) firstly predicts the domain/language label and then extracts mixed domain/language representation to allocate task-level experts in a hierarchical manner; 2) injects the context information to enhance the token routing from the pre-selected task-level experts set, which can help each token to be accurately routed to more specialized and suitable experts. Extensive experiments on multi-domain translation and multilingual translation benchmarks with different architectures consistently demonstrate the superior performance of THOR-MoE. Additionally, the THOR-MoE operates as a plug-and-play module compatible with existing Top-k~citeshazeer2017 and Top-p~citehuang-etal-2024-harder routing schemes, ensuring broad applicability across diverse MoE architectures. For instance, compared with vanilla Top-p~citehuang-etal-2024-harder routing, the context-aware manner can achieve an average improvement of 0.75 BLEU with less than 22% activated parameters on multi-domain translation tasks.