To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales. However, they have inadvertently overlooked the potential of enhancing model reasoning performance by formulating higher-quality problems. In this work, we start from the problem side and propose Self-Polish (SP), a novel method that facilitates the model's reasoning by guiding it to progressively refine the given problems to be more comprehensible and solvable. We also explore several automatic prompting varients and propose the Self-Polish prompt bank for the community. SP is orthogonal to all other prompting methods of answer/reasoning side like CoT, allowing for seamless integration with state-of-the-art techniques for further improvement. Thorough experiments show that the proposed method attains notable and consistent effectiveness on five reasoning benchmarks across different models. Furthermore, our method also showcases impressive performance on robustness evaluation. Codes and prompts are available at https://github.com/WooooDyy/Self-Polish.

翻译：为增强大型语言模型的多步推理能力，研究者已广泛探索提示方法，特别是链式思维（Chain-of-Thought，CoT）方法，该方法明确激发类人推理过程。然而，这些方法无意中忽略了通过构造更高质量问题来提升模型推理表现的可能性。本研究从问题侧出发，提出Self-Polish（SP）这一创新方法——通过引导模型逐步精炼给定问题，使其更易于理解与求解，从而促进模型推理。我们还探索了多种自动提示变体，并为社区提供了Self-Polish提示库。SP与所有其他基于答案/推理侧的提示方法（如CoT）正交，可无缝集成现有最优技术以实现进一步提升。充分实验表明，该方法在五个不同模型的推理基准上均取得了显著且一致的有效性。此外，我们的方法在鲁棒性评估中也展现出卓越表现。代码与提示已开源至 https://github.com/WooooDyy/Self-Polish。