When people think of everyday things like an "egg," they typically have a
mental image associated with it. This commonsense knowledge helps us understand
how these everyday things work and how to interact with them. For example, when
someone tries to make a fried egg, they know that it has a shell and that it
can be cracked open to reveal the egg white and y
本研究旨在探讨语言模型是否具有生成具体执行计划的能力,并针对该问题提出了一个新的问题解决方案: G-PlanET。通过将高级目标和特定环境中物体的数据表输入,我们设计了一种迭代解码策略,并使用新的度量标准 KAS 评估模型执行计划的质量,实验结果表明,将环境信息编码为表格,迭代解码策略可以显著提高语言模型的表现。