利用大语言模型结合思维链推理求解孟加拉语数学应用题
Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning
AI总结：
针对孟加拉语低资源且缺乏数学推理标注数据集的问题，构建了含8792道题的SOMADHAN数据集，评估多种大模型并验证思维链与LoRA微调的效果，推动低资源语言推理研究。
摘要：
由于孟加拉语属于低资源语言，且数学应用题求解需要多步推理，因此孟加拉语数学应用题（MWPs）求解仍是自然语言处理（NLP）领域的一大挑战。现有模型在处理复杂孟加拉语MWPs时表现不佳，主要原因是此前尚无针对该任务的人工标注孟加拉语数据集，这一缺口限制了孟加拉语数学推理方向的研究进展。为解决该问题，我们构建了SOMADHAN数据集，包含8792道复杂孟加拉语MWPs，配有人工编写的分步解答，旨在为语言代表性不足的场景提供支持推理导向评估与模型开发的数据集。基于SOMADHAN，我们采用零样本、少样本提示策略，分别在有无思维链（CoT）推理的设置下，评估了GPT-4o、GPT-3.5 Turbo、LLaMA系列模型、Deepseek、Qwen等多种大语言模型（LLMs）的性能。结果显示，CoT提示相比标准提示持续提升了模型性能，在需要多步逻辑的任务中提升尤为明显；其中LLaMA-3.3 70B在少样本CoT提示下取得了最高88%的准确率。我们还应用低秩适配（LoRA）对模型进行高效微调，使其能以极低计算成本适配孟加拉语MWPs任务。本工作提供了高质量推理数据集与可扩展的复杂MWPs求解框架，填补了孟加拉语NLP领域的关键空白，旨在推动低资源语言的公平研究，提升教育与语言技术中的推理能力。
英文摘要：
Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs, largely because no human-annotated Bengali dataset has previously addressed this task. This gap has limited progress in Bengali mathematical reasoning. To address this, we created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions. We designed this dataset to support reasoning-focused evaluation and model development in a linguistically underrepresented context. Using SOMADHAN, we evaluated a range of large language models (LLMs) - including GPT-4o, GPT-3.5 Turbo, LLaMA series models, Deepseek, and Qwen - through both zero-shot and few-shot prompting with and without Chain of Thought (CoT) reasoning. CoT prompting consistently improved performance over standard prompting, especially in tasks requiring multi-step logic. LLaMA-3.3 70B achieved the highest accuracy of 88% with few-shot CoT prompting. We also applied Low-Rank Adaptation (LoRA) to fine-tune models efficiently, enabling them to adapt to Bengali MWPs with minimal computational cost. Our work fills a critical gap in Bengali NLP by providing a high-quality reasoning dataset and a scalable framework for solving complex MWPs. We aim to advance equitable research in low-resource languages and enhance reasoning capabilities in educational and language technologies.
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。
