Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning

• URL: http://arxiv.org/abs/2510.07300v2
• Date: Tue, 14 Oct 2025 09:32:05 GMT
• Title: Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
• Authors: Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Kaiyu Huang, Yufeng Chen, Jinan Xu, Jie Zhou,
• Abstract summary: We propose M-Thinker, which is trained by a Language Consistency reward and a Cross-lingual Thinking Alignment reward.<n>M-Thinker achieves nearly 100% language consistency and superior performance on two multilingual benchmarks.
• Score: 85.7304930030649
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the "think-then-answer" paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical limitations when processing non-English languages: (1) They often struggle to maintain input-output language consistency; (2) They generally perform poorly with wrong reasoning paths and lower answer accuracy compared to English. These limitations significantly degrade the user experience for non-English speakers and hinder the global deployment of LRMs. To address these limitations, we propose M-Thinker, which is trained by the GRPO algorithm that involves a Language Consistency (LC) reward and a novel Cross-lingual Thinking Alignment (CTA) reward. Specifically, the LC reward defines a strict constraint on the language consistency between the input, thought, and answer. Besides, the CTA reward compares the model's non-English reasoning paths with its English reasoning path to transfer its own reasoning capability from English to non-English languages. Through an iterative RL procedure, our M-Thinker-1.5B/7B models not only achieve nearly 100% language consistency and superior performance on two multilingual benchmarks (MMATH and PolyMath), but also exhibit excellent generalization on out-of-domain languages.

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 Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI [25.42472949919922]
  Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks.<n>When presented with non-English questions, LRMs often default to reasoning in English, raising concerns about interpretability and the handling of linguistic and cultural nuances.
  arXiv  Detail & Related papers  (2025-10-23T15:22:00Z)
• Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective [52.452449102961225]
  This study proposes a novel cross-linguistic perspective to investigate reasoning generalization.<n>Our findings reveal that cross-lingual transferability varies significantly across initial model, target language, and training paradigm.<n>Our study challenges the assumption that LRM reasoning mirrors human cognition, providing critical insights for the development of more language-agnostic LRMs.
  arXiv  Detail & Related papers  (2025-10-02T17:49:49Z)
• Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models [44.94287386776289]
  We identify textbfCross-lingual Collapse, a systematic drift in which a multilingual language model reverts to its dominant pre-training language.<n>Our experiments reveal three key findings: (i) GRPO rapidly amplifies pre-training language imbalances, leading to the erosion of low-resource languages within just a few hundred updates; (ii) language consistency reward mitigates this drift but does so at the expense of an almost 5 - 10 pp drop in accuracy.
  arXiv  Detail & Related papers  (2025-06-06T08:08:48Z)
• 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)
• 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)
• Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models [10.231866835957538]
  Chain-of-thought (CoT) has emerged as a critical mechanism for enhancing reasoning capabilities in large language models (LLMs)<n>We propose the Cross-Lingual Consistency (CLC) framework, which integrates multilingual reasoning paths through majority voting to elevate LLMs' reasoning capabilities.<n> Empirical evaluations on the CMATH dataset reveal CLC's superiority over the conventional self-consistency method.
  arXiv  Detail & Related papers  (2025-04-02T16:09:39Z)
• Demystifying Multilingual Chain-of-Thought in Process Reward Modeling [86.98098988779809]
  We tackle the challenge of extending process reward models (PRMs) to multilingual settings.<n>We train multilingual PRMs on a dataset spanning seven languages, which is translated from English.<n>Our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data.
  arXiv  Detail & Related papers  (2025-02-18T09:11:44Z)

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.