Native Multilingual Chain-of-Thought Reasoning in Low-Resource Southeast Asian Languages

• URL: http://arxiv.org/abs/2608.00533v1
• Date: Sat, 01 Aug 2026 08:44:32 GMT
• Title: Native Multilingual Chain-of-Thought Reasoning in Low-Resource Southeast Asian Languages
• Abstract summary: Onramp-Sequence Cross-Distillation (OSCD) projects high-resource reasoning trajectories into low-resource vocabulary subspaces during generative training rollouts.<n> OSCD yields up to 3.2 times overall improvements in native Southeast Asian languages for mathematical reasoning.
• Score: 3.6077805387487545
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR [2.27726424067057]
  We investigate approaches for transferring knowledge from source languages to low-resource target languages on Whisper.<n>We propose Sequential Adapter Stacking, which places a trainable target-language adapter on top of a frozen source-language adapter.<n>These approaches are evaluated on three target languages unsupported by Whisper.
  arXiv  Detail & Related papers  (2026-09-14T15:43:41Z)
• Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR [6.818862582399845]
  Fine-tuning on low-resource languages often causes catastrophic forgetting.<n>We propose Unified Gradient Projection, which constrains parameter updates using reference gradients from language-balanced replay.<n>On Whisper-large-v3, it achieves near-zero average forgetting.
  arXiv  Detail & Related papers  (2026-07-13T06:57:02Z)
• 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)
• SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment [74.27200765510635]
  We propose SARA (Semantically Anchored Routing Alignment), a framework designed to transfer specialized capabilities from high-resource languages to low-resource languages.<n>We conduct experiments on 2 LLMs across 5 low-resource languages and 3 benchmarks.
  arXiv  Detail & Related papers  (2026-06-24T13:36:46Z)
• IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning [54.28485292978118]
  IRIS is a two-axis framework that combinesSupervised Fine-Tuning on progressively harder problems with Reverse Curriculum Reinforcement Learning.<n>We release CL-Math, a dataset of 29k problems with step-level annotations in English, Hindi, and Marathi.<n>IRIS consistently improves performance across standard benchmarks and curated multilingual test sets.
  arXiv  Detail & Related papers  (2026-04-27T07:10:35Z)
• All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG [87.74635133954975]
  We show that current Multilingual Retrieval-Augmented Generation (mRAG) systems suffer from a language bias during reranking.<n>We propose textittextbfLanguage-textbfAgnostic textbfUtility-driven textbfReranker textbfAlignment (LAURA), which aligns multilingual evidence ranking with downstream generative utility.
  arXiv  Detail & Related papers  (2026-04-22T05:33:06Z)
• MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation [9.42682887916488]
  We introduce a Chinese-centric ALT benchmark for five Southeast Asian low-resource languages (LRLs)<n>In LRLtextrightChinese, fine-tuning and reward-guided optimization dramatically outperform mere model scaling.<n>These results confirm that, in LRLtextrightChinese, targeted data and reward-guided optimization dramatically outperform mere model scaling.
  arXiv  Detail & Related papers  (2026-04-06T16:42:34Z)
• LiRA: Linguistic Robust Anchoring for Cross-lingual Large Language Models [16.504397960476584]
  LiRA (Linguistic Robust Anchoring for Large Language Models) is a training framework that improves cross-lingual representations under low-resource conditions.<n>We release a multilingual product retrieval dataset covering five Southeast Asian and two South Asian languages.
  arXiv  Detail & Related papers  (2025-10-16T09:08:24Z)
• AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought [40.16140566668239]
  We introduce AdaMCOT, a framework that enhances multilingual factual reasoning.<n>AdaMCOT dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses.<n>Our evaluation demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-01-27T15:48:57Z)
• Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing [68.47787275021567]
  Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between latent variables using Optimal Transport.
  arXiv  Detail & Related papers  (2023-07-09T04:52:31Z)
• CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation [113.99145386490639]
  Cross-lingual NER can transfer knowledge between languages via aligned cross-lingual representations or machine translation results. We propose a Cross-lingual Entity Projection framework (CROP) to enable zero-shot cross-lingual NER. We adopt a multilingual labeled sequence translation model to project the tagged sequence back to the target language and label the target raw sentence.
  arXiv  Detail & Related papers  (2022-10-13T13:32:36Z)
• Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation [53.22775597051498]
  We present a continual pre-training framework on mBART to effectively adapt it to unseen languages. Results show that our method can consistently improve the fine-tuning performance upon the mBART baseline. Our approach also boosts the performance on translation pairs where both languages are seen in the original mBART's pre-training.
  arXiv  Detail & Related papers  (2021-05-09T14:49:07Z)

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.