# Question Translation Training for Better Multilingual Reasoning

arXiv: https://arxiv.org/abs/2401.07817 · HTML: https://mlsanity.com/paper/2401.07817/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 15 Jan 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [Extrapolating Large Language Models to Non-English by Aligning Languages](https://mlsanity.com/paper/2308.04948/) (2023)
- [Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations](https://mlsanity.com/paper/2310.20246/) (2023)
- [Revisiting Machine Translation for Cross-lingual Classification](https://mlsanity.com/paper/2305.14240/) (2023)

## Built on by (most cited first, 30 of 42)

- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages](https://mlsanity.com/paper/2407.05975/) (2024)
- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (2025)
- [Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap](https://mlsanity.com/paper/2501.02448/) (2025)
- [Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning](https://mlsanity.com/paper/2502.17407/) (2025)
- [A Survey of Multilingual Reasoning in Language Models](https://mlsanity.com/paper/2502.09457/) (2025)
- [MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment](https://mlsanity.com/paper/2410.05873/) (2024)
- [MindMerger: Efficient Boosting LLM Reasoning in non-English Languages](https://mlsanity.com/paper/2405.17386/) (2024)
- [Language-Specific Latent Process Hinders Cross-Lingual Performance](https://mlsanity.com/paper/2505.13141/) (2025)
- [PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment](https://mlsanity.com/paper/2407.16222/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment](https://mlsanity.com/paper/2501.03681/) (2025)
- [Large Language Models Are Cross-Lingual Knowledge-Free Reasoners](https://mlsanity.com/paper/2406.16655/) (2024)
- [Reasoning Beyond Limits: Advances and Open Problems for LLMs](https://mlsanity.com/paper/2503.22732/) (2025)
- [AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought](https://mlsanity.com/paper/2501.16154/) (2025)
- [Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?](https://mlsanity.com/paper/2510.27269/) (2025)
- [Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners](https://mlsanity.com/paper/2405.13816/) (2024)
- [Improving Multilingual Language Models by Aligning Representations through Steering](https://mlsanity.com/paper/2505.12584/) (2025)
- [Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models](https://mlsanity.com/paper/2506.05850/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment](https://mlsanity.com/paper/2507.14900/) (2025)
- [How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective](https://mlsanity.com/paper/2505.21505/) (2025)
- [The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights](https://mlsanity.com/paper/2405.01345/) (2024)
- [Lens: Rethinking Multilingual Enhancement for Large Language Models](https://mlsanity.com/paper/2410.04407/) (2024)
- [Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments](https://mlsanity.com/paper/2502.17956/) (2025)
- [AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment](https://mlsanity.com/paper/2509.24338/) (2025)
- [Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning](https://mlsanity.com/paper/2503.18484/) (2025)
- [Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From](https://mlsanity.com/paper/2504.10906/) (2025)

## Abstract (arXiv)

Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions. A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training. This approach not only incurs high cost, but also results in poorly translated data due to the non-standard formatting of mathematical chain-of-thought. In this paper, we explore the benefits of question alignment, where we train the model to translate reasoning questions into English by finetuning on X-English parallel question data. In this way we perform targeted, in-domain language alignment which makes best use of English instruction data to unlock the LLMs' multilingual reasoning abilities. Experimental results on LLaMA2-13B show that question alignment leads to consistent improvements over the translate-training approach: an average improvement of 11.3% and 16.1% accuracy across ten languages on the MGSM and MSVAMP multilingual reasoning benchmarks. The project will be available at: https://github.com/NJUNLP/QAlign.