# Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral

arXiv: https://arxiv.org/abs/2403.01851 · HTML: https://mlsanity.com/paper/2403.01851/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)

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

- [Mitigating Catastrophic Forgetting in Language Transfer via Model Merging](https://mlsanity.com/paper/2407.08699/) (2024)
- [Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model](https://mlsanity.com/paper/2404.04167/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [LLMs for Extremely Low-Resource Finno-Ugric Languages](https://mlsanity.com/paper/2410.18902/) (2024)
- [KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication](https://mlsanity.com/paper/2410.16385/) (2024)
- [EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent](https://mlsanity.com/paper/2605.09777/) (2026)

## Abstract (arXiv)

Mixtral, a representative sparse mixture of experts (SMoE) language model, has received significant attention due to its unique model design and superior performance. Based on Mixtral-8x7B-v0.1, in this paper, we propose Chinese-Mixtral and Chinese-Mixtral-Instruct with improved Chinese language abilities by adopting further pre-training and instruction fine-tuning. Experimental results show that our Chinese-Mixtral and Chinese-Mixtral-Instruct successfully improve Chinese understanding and generation performance while retaining the original English abilities. Then, we discuss several key questions when performing language adaptation on large language models, including the necessity of extending the language-specific vocabulary and the choice of the initialization model (foundation model v.s. instruction model), by providing empirical results and analysis. We also present the visualizations of each expert to examine their importance on downstream tasks. Our resources are publicly available through urlhttps://github.com/ymcui/Chinese-Mixtral.