Learning When to Translate for Multilingual Reasoning

• URL: http://arxiv.org/abs/2606.02465v1
• Date: Mon, 01 Jun 2026 16:37:18 GMT
• Title: Learning When to Translate for Multilingual Reasoning
• Abstract summary: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps.<n>English translation can mitigate these failures by expressing non-English inputs in a form that RLMs can more reliably interpret.<n>We propose Luar, a Language Understanding Boundary-aware Reinforcement Learning framework that trains RLMs to selectively invoke translation when direct understanding is unreliable.
• Score: 20.51941069559769
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, largely due to language-understanding failures in non-English inputs. English translation can mitigate these failures by expressing non-English inputs in a form that RLMs can more reliably interpret, yet translating every input is unnecessary when the model can reason reliably from the original query. To address this challenge, we propose Luar, a Language Understanding Boundary-aware Reinforcement Learning framework that trains RLMs to selectively invoke translation when direct understanding is unreliable. Luar trains the model to choose between solving the original input directly and reasoning over its English translation, encouraging translation only when translator-augmented reasoning is expected to substantially outperform direct reasoning. Across multilingual reasoning benchmarks, Luar outperforms standard GRPO and other training-based baselines, with particularly large gains on low-resource languages. Further analysis shows that Luar avoids unnecessary translation in cases where direct reasoning is sufficient, while extending its translator-call behavior to unseen low-resource languages. Together, our work suggests a selective approach to multilingual reasoning: RLMs can learn to invoke translation only when their direct understanding is unreliable. The project will be made publicly available at https://github.com/deokhk/LUAR

Related papers

• Choosing the Right Language Mode at Inference Time for Multilingual Reliability [3.6095388702618405]
  Large language models often struggle to reason in low- to mid-resource languages.<n>Prior work has shown that translation can improve multilingual reasoning by helping models access stronger English-centric representations.<n>This raises a central question: How much translation is needed for multilingual large language models to reason reliably.
  arXiv  Detail & Related papers  (2026-09-04T02:36:26Z)
• Efficient Multilingual Reasoning Transfer via Progressive Code-Switching [51.49388869532955]
  Transfer approaches typically rely on distilled target-language reasoning traces from stronger LRMs or online supervision from external judge models.<n>We propose PCS (Progressive Code-Switching), a more efficient transfer framework that requires only lightweight translation.<n> PCS substantially narrows the performance gap between target-language and English reasoning, yielding more language-consistent reasoning.
  arXiv  Detail & Related papers  (2026-07-01T06:13:16Z)
• AdaMame: A Training Recipe for Adaptive Multilingual Reasoning [32.31269959716733]
  Large Reasoning Models (LRMs) often fail to reason in the language of the query.<n>AdaMame is a two-stage training recipe for multilingual mathematical reasoning.
  arXiv  Detail & Related papers  (2026-06-13T03:22:35Z)
• Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation? [49.7935995447581]
  We investigate whether low-resource machine translation can benefit from structured intermediate steps of linguistic analysis and grammatical reasoning.<n>We propose a pipeline for automatically generating step-by-step linguistic reasoning traces from Universal Dependencies treebanks, dictionaries, and grammar-rule banks.<n>Our results show that linguistic reasoning traces are most effective as inference-time guidance.
  arXiv  Detail & Related papers  (2026-06-02T15:36:12Z)
• Crosslingual On-Policy Self-Distillation for Multilingual Reasoning [48.68444770923683]
  Crosslingual On-Policy Self-Distillation (COPSD) transfers a model's own high-resource reasoning behavior to low-resource languages.<n>Experiments on 17 low-resource African languages show that COPSD consistently improves low-resource mathematical reasoning across model sizes.
  arXiv  Detail & Related papers  (2026-05-10T14:06:09Z)
• 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)
• Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models? [18.99223776816893]
  Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still suffer from a multilingual reasoning gap.<n>This paper shows that the multilingual reasoning gap largely stems from failures in language understanding.<n>We propose Selective Translation, a simple yet effective strategy that translates the multilingual input into English only when an understanding failure is detected.
  arXiv  Detail & Related papers  (2025-10-31T08:17:59Z)
• Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning [85.7304930030649]
  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.
  arXiv  Detail & Related papers  (2025-10-08T17:55:02Z)
• Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning [39.03934159726098]
  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.
  arXiv  Detail & Related papers  (2025-07-07T19:04:36Z)
• 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)
• 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)
• 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)

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.