We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L, GPT-4 and Llama2-70B models, and observe substantial performance gains on various challenging reasoning-intensive tasks including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back Prompting improves PaLM-2L performance on MMLU (Physics and Chemistry) by 7% and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.

翻译：我们提出"后退提示"（Step-Back Prompting）这一简单提示技术，使大型语言模型能够从包含具体细节的实例中抽象出高层次概念和基本原则。利用这些概念和原则引导推理，语言模型在遵循正确推理路径达成解决方案的能力上得到显著提升。我们使用PaLM-2L、GPT-4和Llama2-70B模型对后退提示进行了实验，观察到在包括STEM、知识问答和多跳推理在内的多项高难度推理密集型任务中取得了实质性性能提升。例如，后退提示使PaLM-2L在MMLU（物理和化学）任务上的性能分别提升7%和11%，在TimeQA上提升27%，在MuSiQue上提升7%。