Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
- URL: http://arxiv.org/abs/2507.05418v2
- Date: Fri, 26 Sep 2025 17:57:11 GMT
- Title: Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
- Authors: Jaedong Hwang, Kumar Tanmay, Seok-Jin Lee, Ayush Agrawal, Hamid Palangi, Kumar Ayush, Ila Fiete, Paul Pu Liang,
- Abstract summary: M2A is a novel method that combines multi-scale multilingual alignment with language-consistency rewards on machine-translated questions.<n>We introduce GeoFact-X, a geography-based multilingual factual reasoning benchmark together with reasoning traces in five languages.<n>Our results show that M2A significantly enhances multilingual reasoning fidelity in both mathematical and factual reasoning tasks.
- Score: 39.03934159726098
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) have achieved strong performance in domains like mathematics, factual question answering, and code generation, yet their ability to reason on these tasks in different languages remains underdeveloped. Especially for low-resource languages such as Swahili or Thai, LLMs can often misinterpret prompts or default to reasoning in English. This implicit bias toward high-resource languages undermines factual accuracy, interpretability, and trust. We propose M2A, a novel method that combines multi-scale multilingual alignment with language-consistency rewards on machine-translated questions, training models to reason directly and accurately in the target language. Furthermore, existing multilingual benchmarks only evaluate on final answers, overlooking whether reasoning occurs in the intended language. To close this gap, we introduce GeoFact-X, a geography-based multilingual factual reasoning benchmark together with reasoning traces in five languages: English, Hindi, Japanese, Swahili, and Thai. Our results show that M2A significantly enhances multilingual reasoning fidelity in both mathematical and factual reasoning tasks, highlighting that reasoning-aware multilingual reinforcement learning is crucial for robust cross-lingual generalization. https://jd730.github.io/projects/M2A_GeoFact-X
Related papers
- Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning [71.4175109189942]
We present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR)<n>This approach designates the model's primary language as the pivot language.<n>It establishes a cross-lingual self-feedback mechanism without relying on external correct answers or reward models.
arXiv Detail & Related papers (2026-01-25T03:20:00Z) - The Impact of Language Mixing on Bilingual LLM Reasoning [17.604714678413668]
We study language switching in Chinese-English bilingual reasoning models.<n>We show that language mixing can enhance reasoning.<n>Our findings suggest that language mixing is not merely a byproduct of multilingual training, but is a strategic reasoning behavior.
arXiv Detail & Related papers (2025-07-21T17:56:09Z) - EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning [12.511775058257328]
We investigate whether English is the most token-efficient language for reasoning.<n>We find that reasoning in non-English languages not only reduces token usage, but also preserves accuracy.<n>The extent of improvement depends on the models multilingual strength.
arXiv Detail & Related papers (2025-06-30T20:29:52Z) - MMATH: A Multilingual Benchmark for Mathematical Reasoning [94.05289799605957]
We introduce MMATH, a benchmark for multilingual complex reasoning spanning 374 high-quality math problems across 10 typologically diverse languages.<n>We observe that even advanced models like DeepSeek R1 exhibit substantial performance disparities across languages and suffer from a critical off-target issue-generating responses in unintended languages.<n>Our findings offer new insights and practical strategies for advancing the multilingual reasoning capabilities of large language models.
arXiv Detail & Related papers (2025-05-25T12:47:39Z) - Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
arXiv Detail & Related papers (2025-05-23T02:46:18Z) - When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
arXiv Detail & Related papers (2025-05-21T08:35:05Z) - Crosslingual Reasoning through Test-Time Scaling [51.55526326294275]
We find that scaling up inference compute for English-centric reasoning language models (RLMs) improves multilingual mathematical reasoning across many languages.<n>While English-centric RLM's CoTs are naturally predominantly English, they consistently follow a quote-and-think pattern to reason about quoted non-English inputs.<n>We observe poor out-of-domain reasoning generalization, in particular from STEM to cultural commonsense knowledge, even for English.
arXiv Detail & Related papers (2025-05-08T16:50:06Z) - Scaling Test-time Compute for Low-resource Languages: Multilingual Reasoning in LLMs [3.9530780161144667]
We investigate the multilingual mechanism by which Large Language Models internally operate in a latent space biased toward their inherently dominant language.<n>We train models to generate the chain-of-thought (CoT) in English while outputting the final response in the target language, given input in the low-resource language.<n>Our experiments demonstrate that this approach, named English-Pivoted CoT Training, outperforms other baselines, with up to 28.33% improvement.
arXiv Detail & Related papers (2025-04-02T16:58:36Z) - Assessing Agentic Large Language Models in Multilingual National Bias [31.67058518564021]
Cross-language disparities in reasoning-based recommendations remain largely unexplored.<n>This study is the first to address this gap.<n>We investigate multilingual bias in state-of-the-art LLMs by analyzing their responses to decision-making tasks across multiple languages.
arXiv Detail & Related papers (2025-02-25T08:07:42Z) - The Multilingual Mind : A Survey of Multilingual Reasoning in Language Models [18.399229357408043]
Multilingual reasoning requires language models to handle logical reasoning across languages.<n>This survey provides the first in-depth review of multilingual reasoning in Language Models.
arXiv Detail & Related papers (2025-02-13T16:25:16Z) - Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
arXiv Detail & Related papers (2024-06-28T17:03:51Z) - MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models [65.10456412127405]
MLaKE is a benchmark for the adaptability of knowledge editing methods across five languages.<n>MLaKE aggregates fact chains from Wikipedia across languages and generates questions in both free-form and multiple-choice.<n>We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
arXiv Detail & Related papers (2024-04-07T15:23:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.