改进非洲语言的多语言数学推理
Improving Multilingual Math Reasoning for African Languages
AI总结：
本研究系统评估了将LLM适应非洲语言的不同策略，通过实验比较数据类型、训练阶段等配置，发现最佳适应方法，以提升数学推理性能。
摘要：
从事低资源语言研究的研究人员由于数据可用性有限和计算资源访问受限而面临持续挑战。尽管大多数大型语言模型（LLMs）主要在高资源语言上训练，但将它们适应到低资源环境，特别是非洲语言，需要专门的技术。在当今以多阶段预训练和后训练范式为特征的LLM格局中，已经出现了几种适应低资源语言的策略。然而，最有效的方法仍然不确定。这项工作系统地研究了在将现有LLM扩展到非洲语言时，哪些适应策略能产生最佳性能。我们进行了广泛的实验和消融研究，以评估不同类型的数据组合（翻译数据与合成生成数据）、训练阶段（预训练与后训练）以及其他模型适应配置。我们的实验聚焦于数学推理任务，使用Llama 3.1模型家族作为基础模型。
英文摘要：
Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in high-resource languages, adapting them to low-resource contexts, particularly African languages, requires specialized techniques. Several strategies have emerged for adapting models to low-resource languages in todays LLM landscape, defined by multi-stage pre-training and post-training paradigms. However, the most effective approaches remain uncertain. This work systematically investigates which adaptation strategies yield the best performance when extending existing LLMs to African languages. We conduct extensive experiments and ablation studies to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations. Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
