To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}-\textbf{Re}ading the question as input. Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), which aim to elicit the reasoning process in the output, Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. Consequently, Re2 demonstrates strong generality and compatibility with most thought-eliciting prompting methods, including CoT. Crucially, Re2 facilitates a "bidirectional" encoding in unidirectional decoder-only LLMs because the first pass could provide global information for the second pass. We begin with a preliminary empirical study as the foundation of Re2, illustrating its potential to enable "bidirectional" attention mechanisms. We then evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality. Our findings indicate that, with the exception of a few scenarios on vanilla ChatGPT, Re2 consistently enhances the reasoning performance of LLMs through a simple re-reading strategy. Further analyses reveal Re2's adaptability, showing how it can be effectively integrated with different LLMs, thought-eliciting prompting, and ensemble strategies. Our code is available at \url{https://github.com/Tebmer/Rereading-LLM-Reasoning/}

翻译：为增强现成大型语言模型（LLMs）的推理能力，我们提出一种简单而通用有效的提示方法Re2，即对输入问题进行\textbf{重}-\textbf{重}阅读。与多数旨在激发输出端推理过程的思维引导提示方法（如思维链CoT）不同，Re2通过两次处理问题将关注点转向输入端，从而增强理解过程。因此，Re2展现出强大的通用性，并能与包括CoT在内的大多数思维引导提示方法兼容。关键的是，Re2在单向解码器架构的LLMs中实现了“双向”编码机制，因为首次阅读可为二次阅读提供全局信息。我们首先通过实证研究奠定Re2的理论基础，阐明其实现“双向”注意力机制的潜力。随后在涵盖14个数据集的广泛推理基准测试中开展112组实验，验证Re2的有效性与普适性。研究结果表明，除普通版ChatGPT的少数场景外，Re2通过简单的重读策略持续提升LLMs的推理性能。进一步分析揭示了Re2的适应能力，展示其如何有效整合不同LLMs、思维引导提示及集成策略。代码已发布于\url{https://github.com/Tebmer/Rereading-LLM-Reasoning/}