Fine-tuning large language models (LLMs) with a collection of large and
diverse instructions has improved the model's generalization to different
tasks, even for unseen tasks. However, most existing instruction datasets
include only single instructions, and they struggle to follow complex
instructions composed of multiple subtasks (Wang et al., 2023a). In this work,
we propose a novel concept of compositional instructions called
chain-of-instructions (CoI), where the output of one instruction becomes an
input for the next like a chain. Unlike the conventional practice of solving
single instruction tasks, our proposed method encourages a model to solve each
subtask step by step until the final answer is reached. CoI-tuning (i.e.,
fine-tuning with CoI instructions) improves the model's ability to handle
instructions composed of multiple subtasks. CoI-tuned models also outperformed
baseline models on multilingual summarization, demonstrating the
generalizability of CoI models on unseen composite downstream tasks.

改进大型语言模型的细化调整方法，通过使用多样的组合指令集合，提高了模型对不同任务的泛化性能；引入了链式指令的新概念（CoI），使模型能够处理由多个子任务组成的复合指令，将模型性能在多语言摘要生成任务中进行了验证。

指令链式编排：大型语言模型上的组合指令调整

Chain-of-Instructions: Compositional Instruction Tuning on Large  Language Models

Language is compositional; an instruction can express multiple relation
constraints to hold among objects in a scene that a robot is tasked to
rearrange. Our focus in this work is an instructable scene rearranging
framework that generalizes to longer instructions and to spatial concept
compositions never seen at training time. We propose to represent
language-instructed spatial concepts with energy functions over relative object
arrangements. A language parser maps instructions to corresponding energy
functions and an open-vocabulary visual-language model grounds their arguments
to relevant objects in the scene. We generate goal scene configurations by
gradient descent on the sum of energy functions, one per language predicate in
the instruction. Local vision-based policies then relocate objects to the
inferred goal locations. We test our model on established instruction-guided
manipulation benchmarks, as well as benchmarks of compositional instructions we
introduce. We show our model can execute highly compositional instructions
zero-shot in simulation and in the real world. It outperforms
language-to-action reactive policies and Large Language Model planners by a
large margin, especially for long instructions that involve compositions of
multiple spatial concepts.

通过使用语言解析器将语言指示映射到相应的能量函数，并且使用开放式词汇的视觉语言模型将它们的参数接地到场景中的相关对象，我们提出了一种表示语言指导的空间概念的方法，可以通用于更长的指令和在训练时从未见过的空间概念构成。我们在已建立的指令引导操作基准测试以及我们引介的构成指令基准测试上测试我们的模型，并展示了它在模拟和现实世界中都能够执行高度构成的指令，而且其性能明显优于语言到动作反应策略和大型语言模型计划者，特别是针对涉及多个空间概念构成的长指令。