# Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?

arXiv: https://arxiv.org/abs/2505.17407 · HTML: https://mlsanity.com/paper/2505.17407/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [Do Multilingual LLMs Think In English?](https://mlsanity.com/paper/2502.15603/) (2025)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming](https://mlsanity.com/paper/2410.02677/) (2024)
- [Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction](https://mlsanity.com/paper/2503.03666/) (2025)

## Built on by (most cited first, 20 of 20)

- [Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2510.07300/) (2025)
- [Crosslingual On-Policy Self-Distillation for Multilingual Reasoning](https://mlsanity.com/paper/2605.09548/) (2026)
- [Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners](https://mlsanity.com/paper/2601.02996/) (2026)
- [Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning](https://mlsanity.com/paper/2601.18722/) (2026)
- [TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning](https://mlsanity.com/paper/2603.25419/) (2026)
- [ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance](https://mlsanity.com/paper/2604.12378/) (2026)
- [What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features](https://mlsanity.com/paper/2604.04720/) (2026)
- [The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI](https://mlsanity.com/paper/2510.20647/) (2025)
- [Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages](https://mlsanity.com/paper/2512.02841/) (2025)
- [MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation](https://mlsanity.com/paper/2601.21225/) (2026)
- [Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning](https://mlsanity.com/paper/2601.08267/) (2026)
- [Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch](https://mlsanity.com/paper/2604.15490/) (2026)
- [Efficient Multilingual Reasoning Transfer via Progressive Code-Switching](https://mlsanity.com/paper/2607.00485/) (2026)
- [Learning When to Translate for Multilingual Reasoning](https://mlsanity.com/paper/2606.02465/) (2026)
- [Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs](https://mlsanity.com/paper/2605.27715/) (2026)
- [AdaMame: A Training Recipe for Adaptive Multilingual Reasoning](https://mlsanity.com/paper/2606.15080/) (2026)
- [MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning](https://mlsanity.com/paper/2607.11736/) (2026)
- [RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer](https://mlsanity.com/paper/2608.06347/) (2026)
- [GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings](https://mlsanity.com/paper/2608.13698/) (2026)
- [Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning](https://mlsanity.com/paper/2609.10445/) (2026)

## Abstract (arXiv)

Large reasoning models (LRMs) have demonstrated impressive performance across a range of reasoning tasks, yet little is known about their internal reasoning processes in multilingual settings. We begin with a critical question: it In which language do these models reason when solving problems presented in different languages? Our findings reveal that, despite multilingual training, LRMs tend to default to reasoning in high-resource languages (e.g., English) at test time, regardless of the input language. When constrained to reason in the same language as the input, model performance declines, especially for low-resource languages. In contrast, reasoning in high-resource languages generally preserves performance. We conduct extensive evaluations across reasoning-intensive tasks (MMMLU, MATH-500) and non-reasoning benchmarks (CulturalBench, LMSYS-toxic), showing that the effect of language choice varies by task type: input-language reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior. By exposing these linguistic biases in LRMs, our work highlights a critical step toward developing more equitable models that serve users across diverse linguistic backgrounds.