Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose a novel system that uses language models to perform multi-step logical reasoning. Our system incorporates explicit planning into its inference procedure, thus able to make more informed reasoning decisions at each step by looking ahead into their future effects. In our experiments, our full system significantly outperforms other competing systems. On a multiple-choice question answering task, our system performs competitively compared to GPT-3-davinci despite having only around 1.5B parameters. We conduct several ablation studies to demonstrate that explicit planning plays a crucial role in the system's performance.

翻译：语言模型在广泛的自然语言处理任务中已展现出卓越性能。本文提出了一种新型系统，利用语言模型执行多步逻辑推理。该系统在推理过程中融入了显式规划机制，通过前瞻预测各推理步骤的未来影响，从而在每个环节做出更明智的推理决策。实验结果表明，我们构建的完整系统显著优于其他竞争系统。在多项选择题问答任务中，尽管本系统仅包含约15亿参数，其表现仍能与拥有1750亿参数的GPT-3-davinci模型相匹敌。通过多项消融实验，我们验证了显式规划对系统性能的关键作用。