# Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap

arXiv: https://arxiv.org/abs/2501.02448 · HTML: https://mlsanity.com/paper/2501.02448/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 49 of its 68 references that are in the map.
- First posted on arXiv 5 Jan 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 30 of 49)

- [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)
- [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)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [Analysing Mathematical Reasoning Abilities of Neural Models](https://mlsanity.com/paper/1904.01557/) (2019)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data](https://mlsanity.com/paper/2410.01560/) (2024)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [RedPajama: an Open Dataset for Training Large Language Models](https://mlsanity.com/paper/2411.12372/) (2024)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [KLUE: Korean Language Understanding Evaluation](https://mlsanity.com/paper/2105.09680/) (2021)
- [Benchmarking Benchmark Leakage in Large Language Models](https://mlsanity.com/paper/2404.18824/) (2024)

## Built on by (most cited first, 30 of 43)

- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (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)
- [EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes](https://mlsanity.com/paper/2507.11407/) (2025)
- [R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning](https://mlsanity.com/paper/2502.19735/) (2025)
- [Language-Specific Latent Process Hinders Cross-Lingual Performance](https://mlsanity.com/paper/2505.13141/) (2025)
- [When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners](https://mlsanity.com/paper/2505.15257/) (2025)
- [Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?](https://mlsanity.com/paper/2510.27269/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering](https://mlsanity.com/paper/2601.14050/) (2026)
- [On Code-Induced Reasoning in LLMs](https://mlsanity.com/paper/2509.21499/) (2025)
- [Mi:dm 2.0 Korea-centric Bilingual Language Models](https://mlsanity.com/paper/2601.09066/) (2026)
- [R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning](https://mlsanity.com/paper/2602.05940/) (2026)
- [Multi-Step Reasoning in Korean and the Emergent Mirage](https://mlsanity.com/paper/2501.05712/) (2025)
- [Trillion 7B Technical Report](https://mlsanity.com/paper/2504.15431/) (2025)
- [Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs](https://mlsanity.com/paper/2509.17701/) (2025)
- [Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs](https://mlsanity.com/paper/2605.09063/) (2026)
- [Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub](https://mlsanity.com/paper/2506.00482/) (2025)
- [Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback](https://mlsanity.com/paper/2506.04920/) (2025)
- [EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning](https://mlsanity.com/paper/2507.00246/) (2025)
- [Solar Open 2 Technical Report](https://mlsanity.com/paper/2607.20062/) (2026)
- [K-EXAONE Technical Report](https://mlsanity.com/paper/2601.01739/) (2026)
- [Solar Open Technical Report](https://mlsanity.com/paper/2601.07022/) (2026)
- [x1: Learning to Think Adaptively Across Languages and Cultures](https://mlsanity.com/paper/2604.16917/) (2026)
- [ResearchMath-14K: Scaling Research-Level Mathematics via Agents](https://mlsanity.com/paper/2605.28003/) (2026)
- [Korean Culture into LLM Alignment: Toward Cultural Coherence](https://mlsanity.com/paper/2606.06797/) (2026)
- [Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models](https://mlsanity.com/paper/2503.22968/) (2025)
- [KAIO: A Collection of More Challenging Korean Questions](https://mlsanity.com/paper/2509.14752/) (2025)
- [Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction](https://mlsanity.com/paper/2601.05459/) (2026)
- [Learning When to Translate for Multilingual Reasoning](https://mlsanity.com/paper/2606.02465/) (2026)

## Abstract (arXiv)

Large language models (LLMs) demonstrate exceptional performance on complex reasoning tasks. However, despite their strong reasoning capabilities in high-resource languages (e.g., English and Chinese), a significant performance gap persists in other languages. To investigate this gap in Korean, we introduce HRM8K, a benchmark comprising 8,011 English-Korean parallel bilingual math problems. Through systematic analysis of model behaviors, we identify a key finding: these performance disparities stem primarily from difficulties in comprehending non-English inputs, rather than limitations in reasoning capabilities. Based on these findings, we propose UST (Understand, Solve, and Translate), a method that strategically uses English as an anchor for reasoning and solution generation. By fine-tuning the model on 130k synthetically generated data points, UST achieves a 10.91% improvement on the HRM8K benchmark and reduces the multilingual performance gap from 11.6% to 0.7%. Additionally, we show that improvements from UST generalize effectively to different Korean domains, demonstrating that capabilities acquired from machine-verifiable content can be generalized to other areas. We publicly release the benchmark, training dataset, and models.