In everyday life, humans often plan their actions by following step-by-step instructions in the form of goal-oriented scripts. Previous work has exploited language models (LMs) to plan for abstract goals of stereotypical activities (e.g., "make a cake"), but leaves more specific goals with multi-facet constraints understudied (e.g., "make a cake for diabetics"). In this paper, we define the task of constrained language planning for the first time. We propose an overgenerate-then-filter approach to improve large language models (LLMs) on this task, and use it to distill a novel constrained language planning dataset, CoScript, which consists of 55,000 scripts. Empirical results demonstrate that our method significantly improves the constrained language planning ability of LLMs, especially on constraint faithfulness. Furthermore, CoScript is demonstrated to be quite effective in endowing smaller LMs with constrained language planning ability.

翻译：在日常生活中，人类通常通过遵循目标导向的脚本中的逐步指令来规划自己的行动。以往的研究利用语言模型（LMs）来规划典型活动的抽象目标（例如“制作蛋糕”），但较少关注具有多方面约束的更具体目标（例如“为糖尿病患者制作蛋糕”）。本文首次定义了受限语言规划任务。我们提出了一种“过生成-再过滤”的方法来改进大语言模型（LLMs）在该任务上的表现，并利用该方法蒸馏出一个新颖的受限语言规划数据集CoScript，该数据集包含55,000个脚本。实验结果表明，我们的方法显著提升了LLMs的受限语言规划能力，尤其是在约束忠实度方面。此外，CoScript在赋予较小语言模型受限语言规划能力方面表现出显著效果。