paper-with-me

홈 › Papers

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

2024-01-13 · Linzheng Chai, Jian Yang, Tao Sun, Hongcheng Guo, Jiaheng Liu, Bing Wang, Xiannian Liang, Jiaqi Bai, Tongliang Li, Qiyao Peng, Zhoujun Li

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages. Specifically, the multilingual instruction training data (xCOT-INSTRUCT) is created to encourage the semantic alignment of multiple languages. We introduce cross-lingual in-context few-shot learning (xICL)) to accelerate multilingual agreement in instruction tuning, where some fragments of source languages in examples are randomly substituted by their counterpart translations of target languages. During multilingual instruction tuning, we adopt the randomly online CoT strategy to enhance the multilingual reasoning ability of the large language model by first translating the query to another language and then answering in English. To further facilitate the language transfer, we leverage the high-resource CoT to supervise the training of low-resource languages with cross-lingual distillation. Experimental results on previous benchmarks demonstrate the superior performance of xCoT in reducing the gap among different languages, highlighting its potential to reduce the cross-lingual gap.

📄 PDF Abstract BibTeX arXiv:2401.07037

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation

2025-07-17 · Weihua Zheng, Roy Ka-Wei Lee, Zhengyuan Liu, Kui Wu 외 arxiv

Multilingual Large Language Models(MLLMs) demonstrate strong generalization across languages, yet they remain prone to hallucinations, especially in low-resource languages, due to training data imbalances. These hallucin…

Contrastive Learning

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework

2026-04-22 · Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian 외 arxiv

Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning, yet existing methods remain costly due to extensive sampling of full trajectories across languages. Moreover, multilin…

Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning

2024-06-13 · Janghoon Han, Changho Lee, Joongbo Shin, Stanley Jungkyu Choi 외

Instruction tuning has emerged as a powerful technique, significantly boosting zero-shot performance on unseen tasks. While recent work has explored cross-lingual generalization by applying instruction tuning to multilin…

Zero-shot Generalization

Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions?

2024-02-21 · Alexander Arno Weber, Klaudia Thellmann, Jan Ebert, Nicolas Flores-Herr 외

The adaption of multilingual pre-trained LLMs into eloquent and helpful assistants is essential to facilitate their use across different language regions. In that spirit, we are the first to conduct an extensive study of…

Instruction Following

Multilingual Instruction Tuning With Just a Pinch of Multilinguality

2024-01-03 · Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor 외

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during ins…

Cross-Lingual TransferInstruction Following