# Mix-of-Language-Experts Architecture for Multilingual Programming

arXiv: https://arxiv.org/abs/2506.18923 · HTML: https://mlsanity.com/paper/2506.18923/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 47 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://mlsanity.com/paper/2404.02948/) (2024)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA](https://mlsanity.com/paper/2312.03732/) (2023)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)
- [LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning](https://mlsanity.com/paper/2308.03303/) (2023)
- [LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters](https://mlsanity.com/paper/2405.17604/) (2024)
- [PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback](https://mlsanity.com/paper/2307.14936/) (2023)
- [Upcycling Large Language Models into Mixture of Experts](https://mlsanity.com/paper/2410.07524/) (2024)

## Built on by (most cited first, 3 of 3)

- [Grow Up and Merge: Scaling Strategies for Efficient Language Adaptation](https://mlsanity.com/paper/2512.10772/) (2025)
- [COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling](https://mlsanity.com/paper/2604.20720/) (2026)
- [LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation](https://mlsanity.com/paper/2609.18959/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive capabilities in aiding developers with tasks like code comprehension, generation, and translation. Supporting multilingual programming -- i.e., coding tasks across multiple programming languages -- typically requires either (1) finetuning a single LLM across all programming languages, which is cost-efficient but sacrifices language-specific specialization and performance, or (2) finetuning separate LLMs for each programming language, which allows for specialization but is computationally expensive and storage-intensive due to the duplication of parameters. This paper introduces MoLE (Mix-of-Language-Experts), a novel architecture that balances efficiency and specialization for multilingual programming. MoLE is composed of a base model, a shared LoRA (low-rank adaptation) module, and a collection of language-specific LoRA modules. These modules are jointly optimized during the finetuning process, enabling effective knowledge sharing and specialization across programming languages. During inference, MoLE automatically routes to the language-specific LoRA module corresponding to the programming language of the code token being generated. Our experiments demonstrate that MoLE achieves greater parameter efficiency compared to training separate language-specific LoRAs, while outperforming a single shared LLM finetuned for all programming languages in terms of accuracy.