SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models

Domain:

natural language processing

Record type:

papermodel

Creator:

Qi,ManCheMo,

Host:

Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource languages due to resource constraints, which struggles with multilingual reasoning tasks. To this end, we propose Structured-of-Thought (SoT), a training-free method that improves the performance on multilingual reasoning through a multi-step transformation: Language Thinking Transformation and Structured Knowledge Transformation. The SoT method converts language-specific semantic information into language-agnostic structured representations, enabling the models to understand the query in different languages more sophisticated. Besides, SoT effectively guides LLMs toward more concentrated reasoning to maintain consistent underlying reasoning pathways when handling cross-lingual variations in expression. Experimental results demonstrate that SoT outperforms several strong baselines on multiple multilingual reasoning benchmarks when adapting to various backbones of LLMs. It can also be integrated with other training-free strategies for further improvements. Our code is available at github.com. EMNLP 2025 (findings)

Visit

arxiv.org

Language Models are Multilingual Chain-of-Thought Reasoners

We evaluate the reasoning abilities of large language models in multilingual settings. We introduce

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners

Large reasoning models (LRMs) achieve strong performance on mathematical reasoning tasks, often attr

Quantifying Language Disparities in Multilingual Large Language Models

Results reported in large-scale multilingual evaluations are often fragmented and confounded by fact

Bridging language gaps in multilingual large language models

Large language models (LLMs) have revolutionized natural language processing, yet significant perfor

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million p

Linguistic Relativity Meets Large Language Models: Does Prompting in Yorùbá Elicit Qualitatively Different AI Outputs Than Prompting in English?

The Sapir-Whorf hypothesis of linguistic relativity posits that the language one uses shape