微调大模型可精准控制航天系统，且数据需求少、泛化能力强。
Fine-Tuned Language Models as Space Systems Controllers
- 用70亿到130亿参数的小型语言模型，通过微调实现多维航天控制。
- 在四个任务中生成精度达10位有效数字的控制向量，所需数据少于传统神经网络。
- 同一模型可跨任务微调，性能损失小，适合构建通用航天控制器。
大型语言模型（LLMs）或基础模型（FMs）是经过预训练的Transformer模型，能自回归地连贯完成句子。本文表明，对小型语言模型（70亿至130亿参数）进行额外训练（即微调）后，可控制简化的空间系统。我们关注四个问题：三维弹簧玩具系统、低推力轨道转移、低推力地月控制及动力下降引导。微调后的语言模型能生成多维输出向量，精度高达10位有效数字。实验显示，完成微调所需数据量小于传统深度神经网络（DNNs），且模型在训练集外具有良好泛化能力。此外，同一模型可使用不同任务的数据进行微调，仅出现轻微性能下降，优于针对单一任务训练的模型。本工作旨在为通用空间系统控制器的发展迈出第一步。
原文摘要 · Abstract (English)
Large language models (LLMs), or foundation models (FMs), are pretrained transformers that coherently complete sentences auto-regressively. In this paper, we show that LLMs can control simplified space systems after some additional training, called fine-tuning. We look at relatively small language models, ranging between 7 and 13 billion parameters. We focus on four problems: a three-dimensional spring toy problem, low-thrust orbit transfer, low-thrust cislunar control, and powered descent guidance. The fine-tuned LLMs are capable of controlling systems by generating sufficiently accurate outputs that are multi-dimensional vectors with up to 10 significant digits. We show that for several problems the amount of data required to perform fine-tuning is smaller than what is generally required of traditional deep neural networks (DNNs), and that fine-tuned LLMs are good at generalizing outside of the training dataset. Further, the same LLM can be fine-tuned with data from different problems, with only minor performance degradation with respect to LLMs trained for a single application. This work is intended as a first step towards the development of a general space systems controller.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。