Skip to content

What Does Post-Training Change in Multilingual Reasoning?

Sep 2026 · arXiv.org · Vol abs/2609.37104 · 0 citations · 23 references
Computer Science

TL;DR

These stages establish a constructive post-training path from English-pivoted capability to multilingual reasoning that is reliably delivered, and jointly track correctness, language adherence, termination, and delivery efficiency.

Abstract

Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a complete solution in the user's language, language becomes an access barrier rather than merely a source of performance variation. We audit Qwen3 checkpoints on competition-mathematics tasks in eleven languages. Across the ten non-English languages, only 15.4-17.9% of problems receive a correct, terminating solution with visible reasoning in the requested language in any of 16 samples, compared with 92.9% in English. To identify the source of this disparity, we evaluate thirteen endpoints from one model family, spanning released checkpoints, multilingual supervised fine-tuning (SFT) at two scales, controlled SFT ablations, and three reinforcement-learning (RL) reward formulations. We jointly track correctness, language adherence, termination, and delivery efficiency. The dominant bottleneck shifts across post-training stages. Released models often reason in English. Multilingual SFT restores target-language reasoning, but accuracy declines across multilingual, English-only, and single-language SFT runs, showing that this cost is not specific to multilingual mixing; non-English reasoning traces additionally become prone to non-terminating loops. RL restores termination in both arms at no cost in accuracy, but only the arm whose reward includes a language term delivers: rewarding correctness alone returns the model to English. Together, these stages establish a constructive post-training path from English-pivoted capability to multilingual reasoning that is reliably delivered.

View source

Similar papers

#natural language process... Preprint Sep 2026

Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning

It is shown the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone, indicating that reasoning is a language-agnostic behavior that can be transferred across typologically diverse l...

Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca et al. · 0 citations
Preprint Aug 2026

Skill Issue: Are Skills Language-Invariant in LLMs?

This work quantifies cross-lingual skill inconsistency orthogonally from knowledge and general benchmark performance via multilingual self-play, and shows that skill discrepancies are a measurable major roadblock in the development of truly multilingual models.

Bobby Cheng, Adam Gaber, Zhengzhe Liu et al. · 1 citation
Preprint Aug 2026

When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

It is found that, in this benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy and, under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement lear...

Siddharth Chauhan, Thomas Butler, Abhishek Singhania et al. · 0 citations
#natural language process... Open access Sep 2026

Choosing the Right Language Mode at Inference Time for Multilingual Reliability

Reliability-Aware Adaptive Inference (RAAI), a training-free test-time framework that performs Expected Calibration Error-aware routing and prompt fusion, and uses a mid-layer Risk Index to gate sequential reasoning, allocating compute only when it is likely to help and suppressing harmful bilingual redundancy, is addr...

Ekata Mitra, Ameeta Agrawal · 0 citations
#artificial intelligence Preprint Sep 2026

UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms

A unified reasoning reward model supporting multiple languages and evaluation paradigms, UniRRM uses a staged reasoning chain to dynamically generate task-generic and instruction-specific criteria, enabling fine-grained, input-adaptive judgments while maintaining consistency across languages.

Peng Lai, Yi-Chao Du, Junchao Wu et al. · 1 citation
Preprint Aug 2026

GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings

It is found that training to reason in the native language often leaves only a small gap to training for English reasoning, and RLVR beyond English can provide broad crosslingual gains, but also requires broad evaluation to detect language-specific regressions.

Konstantin Dobler, Federico Scozzafava, Jonathan Janke et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.