# LLaMA Beyond English: An Empirical Study on Language Capability Transfer

arXiv: https://arxiv.org/abs/2401.01055 · HTML: https://mlsanity.com/paper/2401.01055/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 2 Jan 2024.

## Builds on (most cited first, 28 of 28)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Evaluating the Performance of Large Language Models on GAOKAO Benchmark](https://mlsanity.com/paper/2305.12474/) (2023)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models](https://mlsanity.com/paper/2010.06189/) (2020)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Finding Universal Grammatical Relations in Multilingual BERT](https://mlsanity.com/paper/2005.04511/) (2020)
- [GLUECoS : An Evaluation Benchmark for Code-Switched NLP](https://mlsanity.com/paper/2004.12376/) (2020)
- [Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation](https://mlsanity.com/paper/2305.15011/) (2023)
- [Are Multilingual Models Effective in Code-Switching?](https://mlsanity.com/paper/2103.13309/) (2021)
- [NusaCrowd: Open Source Initiative for Indonesian NLP Resources](https://mlsanity.com/paper/2212.09648/) (2022)
- [Zero-shot cross-lingual transfer language selection using linguistic similarity](https://mlsanity.com/paper/2301.13720/) (2023)
- [Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling](https://mlsanity.com/paper/2103.07792/) (2021)
- [Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots](https://mlsanity.com/paper/2103.09593/) (2021)
- [Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies](https://mlsanity.com/paper/2202.12312/) (2022)
- [Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition](https://mlsanity.com/paper/1909.08504/) (2019)

## Built on by (most cited first, 30 of 95)

- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM](https://mlsanity.com/paper/2403.07816/) (2024)
- [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://mlsanity.com/paper/2402.11548/) (2024)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [From Tokens to Words: On the Inner Lexicon of LLMs](https://mlsanity.com/paper/2410.05864/) (2024)
- [Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages](https://mlsanity.com/paper/2402.12204/) (2024)
- [SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages](https://mlsanity.com/paper/2407.19672/) (2024)
- [Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding](https://mlsanity.com/paper/2406.15481/) (2024)
- [Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs](https://mlsanity.com/paper/2406.09265/) (2024)
- [MaLA-500: Massive Language Adaptation of Large Language Models](https://mlsanity.com/paper/2401.13303/) (2024)
- [Language Imbalance Driven Rewarding for Multilingual Self-improving](https://mlsanity.com/paper/2410.08964/) (2024)
- [Code-Switching Curriculum Learning for Multilingual Transfer in LLMs](https://mlsanity.com/paper/2411.02460/) (2024)
- [Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model](https://mlsanity.com/paper/2404.04167/) (2024)
- [Unveiling Linguistic Regions in Large Language Models](https://mlsanity.com/paper/2402.14700/) (2024)
- [Exploring Design Choices for Building Language-Specific LLMs](https://mlsanity.com/paper/2406.14670/) (2024)
- [Egalitarian Language Representation in Language Models: It All Begins with Tokenizers](https://mlsanity.com/paper/2409.11501/) (2024)
- [Sailor: Open Language Models for South-East Asia](https://mlsanity.com/paper/2404.03608/) (2024)
- [Poro 34B and the Blessing of Multilinguality](https://mlsanity.com/paper/2404.01856/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://mlsanity.com/paper/2402.14714/) (2024)
- [Language Models' Factuality Depends on the Language of Inquiry](https://mlsanity.com/paper/2502.17955/) (2025)
- [TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese](https://mlsanity.com/paper/2401.16640/) (2024)
- [Evaluating Contextually Personalized Programming Exercises Created with Generative AI](https://mlsanity.com/paper/2407.11994/) (2024)
- [Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian](https://mlsanity.com/paper/2405.13929/) (2024)
- [Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models](https://mlsanity.com/paper/2412.13702/) (2024)
- [RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs](https://mlsanity.com/paper/2502.07424/) (2025)
- [Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?](https://mlsanity.com/paper/2403.01929/) (2024)

## Abstract (arXiv)

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant corpus, which limits their performance in other non-English languages. In this paper, we focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. To answer this question, we conduct an extensive empirical investigation based on LLaMA, accumulating over 1440 GPU hours. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. To accurately assess the model's level of knowledge, we employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench. Furthermore, a comprehensive evaluation of the model's response quality is conducted, considering aspects such as accuracy, fluency, informativeness, logical coherence, and harmlessness, based on LLM-Eval, a benchmarks consisting instruction tasks from 17 diverse categories. Our evaluation results demonstrate that comparable performance to state-of-the-art transfer models can be achieved with less than 1% of the pretraining data, both in terms of knowledge alignment and response quality. Furthermore, the experimental outcomes across the thirteen low-resource languages also exhibit similar trends. We anticipate that the conclusions revealed by the experiments will aid the community in developing non-English LLMs.