Large language models (LLMs) still grapple with complex tasks like mathematical reasoning. Despite significant efforts invested in improving prefix prompts or reasoning process, the crucial role of problem context might have been neglected. Accurate recognition of inputs is fundamental for solving mathematical tasks, as ill-formed problems could potentially mislead LLM's reasoning. In this study, we propose a new approach named Problem Elaboration Prompting (PEP) to enhance the mathematical capacities of LLMs. Specifically, PEP decomposes and elucidates the problem context before reasoning, therefore enhancing the context modeling and parsing efficiency. Experiments across datasets and models demonstrate promising performances: (1) PEP demonstrates an overall enhancement in various mathematical tasks. For instance, with the GPT-3.5 model, PEP exhibits improvements of 9.93% and 8.80% on GSM8k through greedy decoding and self-consistency, respectively. (2) PEP can be easily implemented and integrated with other prompting methods. (3) PEP shows particular strength in handling distraction problems.

翻译：大语言模型（LLMs）在数学推理等复杂任务中仍存在挑战。尽管在改进前缀提示或推理过程方面投入了大量努力，但问题语境的关键作用可能被忽视了。准确识别输入是解决数学任务的基础，因为形式有缺陷的问题可能会误导LLM的推理。在本研究中，我们提出了一种名为问题细化提示（PEP）的新方法，以增强LLM的数学能力。具体而言，PEP在推理之前对问题语境进行分解和阐释，从而提升语境建模和解析效率。跨数据集和模型的实验展示了其显著性能：（1）PEP在各种数学任务中均表现出整体提升。例如，使用GPT-3.5模型时，通过贪婪解码和自一致性方法，PEP在GSM8k数据集上分别提升了9.93%和8.80%。（2）PEP易于实现，可与其他提示方法集成。（3）PEP在处理干扰问题方面展现出独特优势。