The Onramp-Sequence Cross-Distillation (OSCD) is introduced, a post-training algorithm that projects high-resource reasoning trajectories into low-resource vocabulary subspaces during generative training rollouts via an integrated translator agentic loop, ensuring the stable and efficient translation of dynamically generated reference samples for fine-tuning.
Abstract
Large Language Models have achieved substantial progress in reasoning capabilities. Yet in low-resource native settings, many suffer from cross-lingual collapse, reverting to English during intermediate steps that require complex logical reasoning. This presents a cold-start bottleneck for policy optimization, whereas standard fine-tuning risks catastrophic forgetting due to cross-lingual representation drift. To address these challenges, we introduce the Onramp-Sequence Cross-Distillation (OSCD), a post-training algorithm that projects high-resource reasoning trajectories into low-resource vocabulary subspaces during generative training rollouts via an integrated translator agentic loop, ensuring the stable and efficient translation of dynamically generated reference samples for fine-tuning. This is coupled with joint-embedding semantic alignment of both reference and target-language reasoning traces, thereby bridging the pairwise cross-lingual representational gaps. Comprehensive evaluations using the AIME25 and HMMT25 benchmarks demonstrate that OSCD yields up to 3.2 times overall improvements in native Southeast Asian languages for mathematical reasoning, of which the joint-embedding semantic alignment component contributes up to 6.4% improvements in linguistic debiasing over translation-only baselines.
Experiments on multilingual mathematical benchmarks show that MCD consistently reduces reasoning length while maintaining competitive accuracy, and significantly improves robustness in low-resource languages.
Jiarui Wan, Songming Zhang, Yufeng Chen· Proceedings of the 1st Works...· 0 citations
Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.
Daryna Dementieva, N. Babakov, Kathy Hammerl et al.· 0 citations
Large language models continue to face challenges in translating low-resource languages with scarce parallel data. This study investigates how to fine-tune them effectively using target-side monolingual data. Existing approaches—dominated by back-translation and recent LLM-based rewriting—remain limited by noisy synthetic sources, unguided simplification, and the absence of a principled mechanism for integrating monolingual sentences into the training objective. To address this, we developed a semi-supervised framework that integrates marginal distribution estimation and curriculum-guided rewriting to exploit monolingual data for low-resource translation. Experiments in four low-resource directions demonstrated substantial gains, averaging +8 spBLEU and +10 COMET over strong baselines, while three additional mid-resource directions showed stable improvements and consistent trends. Reference-free metrics further validated robust gains in fluency and adequacy. The findings establish a scalable paradigm for low-resource translation, revealing that the principled integration of marginal likelihood estimation and generative rewriting enables large language models to achieve superior performance under extreme data scarcity.
Wenjie Yu, Zhiqiang Yu, Zuo Jiang et al.· ACM Transactions on Asian an...· 0 citations
LatentMT is introduced, the first systematic study of latent-reasoning LoopLMs for machine translation that adapts a small 2.6B-parameter backbone model with lightweight training and shows that hidden-representation differences shrink along the recurrent reasoning-step axis, supporting the observed saturation in performance.
Wei-Rui Chen, Samar M. Magdy, Chiyu Zhang et al.· 0 citations
The results indicate that a moderately sized, shared self-attention architecture can deliver production-quality multilin-gual translation within the resource constraints of an academic de-ployment, while surfacing clear directions – low-resource language coverage, domain adaptation, and speech-based extension – for con-tinued development.
Darshan Gowda D H and Dr. Kruti R· International Journal of Adv...· 0 citations
Progressive Code-Switching (Progressive Code-Switching) is proposed, a more efficient transfer framework that requires only lightweight translation without any stronger model for distillation or judging for target-language reasoning.