# Cross-Lingual Optimization for Language Transfer in Large Language Models

arXiv: https://arxiv.org/abs/2505.14297 · HTML: https://mlsanity.com/paper/2505.14297/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://mlsanity.com/paper/2405.21046/) (2024)
- [LLaMA Beyond English: An Empirical Study on Language Capability Transfer](https://mlsanity.com/paper/2401.01055/) (2024)
- [WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models](https://mlsanity.com/paper/2112.06598/) (2021)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [Multilingual Instruction Tuning With Just a Pinch of Multilinguality](https://mlsanity.com/paper/2401.01854/) (2024)
- [From English To Foreign Languages: Transferring Pre-trained Language Models](https://mlsanity.com/paper/2002.07306/) (2020)
- [AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging](https://mlsanity.com/paper/2402.18913/) (2024)
- [Adapting Monolingual Models: Data can be Scarce when Language Similarity is High](https://mlsanity.com/paper/2105.02855/) (2021)
- [InstructionCP: A fast approach to transfer Large Language Models into target language](https://mlsanity.com/paper/2405.20175/) (2024)
- [Dynamic data sampler for cross-language transfer learning in large language models](https://mlsanity.com/paper/2405.10626/) (2024)

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

- [Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models](https://mlsanity.com/paper/2606.01464/) (2026)
- [Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning](https://mlsanity.com/paper/2610.00320/) (2026)

## Abstract (arXiv)

Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments. To overcome these challenges, we propose Cross-Lingual Optimization (CLO) that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities. CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer. We conduct experiments using five models on six languages, each possessing varying levels of resource. Our results show that CLO consistently outperforms SFT in both acquiring target language proficiency and maintaining English performance. Remarkably, in low-resource languages, CLO with only 3,200 samples surpasses SFT with 6,400 samples, demonstrating that CLO can achieve better performance with less data. Furthermore, we find that SFT is particularly sensitive to data quantity in medium and low-resource languages, whereas CLO remains robust. Our comprehensive analysis emphasizes the limitations of SFT and incorporates additional training strategies in CLO to enhance efficiency.