# MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completion

arXiv: https://arxiv.org/abs/2212.09666 · HTML: https://mlsanity.com/paper/2212.09666/

## Key facts

- Cited by 6 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 29 of its 39 references that are in the map.
- First posted on arXiv 19 Dec 2022.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1604.02201/) (2016)
- [DEMix Layers: Disentangling Domains for Modular Language Modeling](https://mlsanity.com/paper/2108.05036/) (2021)
- [Multilingual is not enough: BERT for Finnish](https://mlsanity.com/paper/1912.07076/) (2019)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Multilingual Neural Machine Translation with Knowledge Distillation](https://mlsanity.com/paper/1902.10461/) (2019)
- [SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation](https://mlsanity.com/paper/2108.04556/) (2021)
- [Multi-task Learning based Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2012.14631/) (2020)
- [CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences](https://mlsanity.com/paper/2202.06689/) (2022)
- [PyTorrent: A Python Library Corpus for Large-scale Language Models](https://mlsanity.com/paper/2110.01710/) (2021)
- [Zero-Shot Paraphrase Generation with Multilingual Language Models](https://mlsanity.com/paper/1911.03597/) (2019)

## Built on by (most cited first, 6 of 6)

- [Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat](https://mlsanity.com/paper/2401.17163/) (2024)
- [The potential of LLMs for coding with low-resource and domain-specific programming languages](https://mlsanity.com/paper/2307.13018/) (2023)
- [SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning](https://mlsanity.com/paper/2511.19422/) (2025)
- [Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities](https://mlsanity.com/paper/2409.01382/) (2024)
- [NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation](https://mlsanity.com/paper/2504.18147/) (2025)
- [Investigating the Transferability of Code Repair for Low-Resource Programming Languages](https://mlsanity.com/paper/2406.14867/) (2024)

## Abstract (arXiv)

Code completion is a valuable topic in both academia and industry. Recently, large-scale mono-programming-lingual (MonoPL) pre-training models have been proposed to boost the performance of code completion. However, the code completion on low-resource programming languages (PL) is difficult for the data-driven paradigm, while there are plenty of developers using low-resource PLs. On the other hand, there are few studies exploring the effects of multi-programming-lingual (MultiPL) pre-training for the code completion, especially the impact on low-resource programming languages. To this end, we propose the MultiCoder to enhance the low-resource code completion via MultiPL pre-training and MultiPL Mixture-of-Experts (MoE) layers. We further propose a novel PL-level MoE routing strategy (PL-MoE) for improving the code completion on all PLs. Experimental results on CodeXGLUE and MultiCC demonstrate that 1) the proposed MultiCoder significantly outperforms the MonoPL baselines on low-resource programming languages, and 2) the PL-MoE module further boosts the performance on six programming languages. In addition, we analyze the effects of the proposed method in details and explore the effectiveness of our method in a variety of scenarios.