arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.16588cs.LGcs.SYeess.SY
收藏

微调语言模型作为空间系统控制器

Fine-Tuned Language Models as Space Systems Controllers

Massachusetts Institute of Technology(麻省理工学院);Universidad Politécnica de Madrid(马德里理工大学)

Enrico M. Zucchelli, Di Wu, Julia Briden, Christian Hofmann, Victor Rodriguez-Fernandez, Richard Linares

AI总结:

本文表明经过微调的7至13B参数LLMs能控制简化空间系统,在四个问题上生成高精度多维向量,所需数据量少于传统DNNs且泛化良好,为通用空间系统控制器迈出第一步。

摘要:

大型语言模型(LLMs),或基础模型(FMs),是自回归地连贯补全句子的预训练transformers。在本文中,我们展示了LLMs在经过一些称为微调的额外训练后,可以控制简化的空间系统。我们研究了相对较小的语言模型,参数量在7到13 billion之间。我们关注四个问题:三维弹簧玩具问题、低推力轨道转移、低推力地月空间控制以及动力下降制导。微调后的LLMs能够通过生成足够精确的输出(即最多包含10位有效数字的多维向量)来控制系统。我们表明,对于几个问题,执行微调所需的数据量小于传统深度神经网络(DNNs)通常所需的数据量,并且微调后的LLMs在训练数据集之外具有良好的泛化能力。此外,同一个LLM可以使用不同问题的数据进行微调,与为单一应用训练的LLMs相比,性能仅有轻微下降。这项工作旨在作为开发通用空间系统控制器的第一步。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑