Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
This addresses the issue of language bias in LLMs for users in multilingual and low-resource language contexts, representing a novel approach to enhancing cross-lingual generalization.
The paper tackles the problem of large language models (LLMs) underperforming in reasoning tasks for low-resource languages by proposing M2A, a method that improves multilingual reasoning fidelity, and introduces GeoFact-X, a benchmark to evaluate reasoning in multiple languages.
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