负责任的任务自动化：赋能大型语言模型作为负责任的任务自动化者

Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators

June 2, 2023

作者: Zhizheng Zhang, Xiaoyi Zhang, Wenxuan Xie, Yan Lu

cs.AI

摘要

大型语言模型（LLMs）最近取得的成功标志着人工通用智能迈出了令人瞩目的一步。它们展现出在用户指令下自动完成任务的前景，并充当类似大脑的协调者。随着我们将越来越多的任务委托给机器进行自动化完成，相关风险将逐渐显现。一个重要问题浮现：在帮助人类自动化任务作为个人副驾驶员时，我们如何确保机器行为负责？本文从可行性、完整性和安全性的角度深入探讨这个问题。具体而言，我们提出了“负责任任务自动化”（Responsible Task Automation，ResponsibleTA）作为一个基础框架，以促进基于LLM的协调者与执行者之间负责任的任务自动化合作，具备三种增强能力：1）预测执行者命令的可行性；2）验证执行者的完整性；3）增强安全性（例如，保护用户隐私）。我们进一步提出并比较了实现前两种能力的两种范式。一种是通过提示工程利用LLMs本身的通用知识，另一种是采用领域特定的可学习模型。此外，我们引入了本地存储机制来实现第三种能力。我们在UI任务自动化上评估了我们提出的ResponsibleTA，并希望它能引起更多关于在不同场景中确保LLMs更加负责任的关注。研究项目主页位于https://task-automation-research.github.io/responsible_task_automation。

English

The recent success of Large Language Models (LLMs) signifies an impressive stride towards artificial general intelligence. They have shown a promising prospect in automatically completing tasks upon user instructions, functioning as brain-like coordinators. The associated risks will be revealed as we delegate an increasing number of tasks to machines for automated completion. A big question emerges: how can we make machines behave responsibly when helping humans automate tasks as personal copilots? In this paper, we explore this question in depth from the perspectives of feasibility, completeness and security. In specific, we present Responsible Task Automation (ResponsibleTA) as a fundamental framework to facilitate responsible collaboration between LLM-based coordinators and executors for task automation with three empowered capabilities: 1) predicting the feasibility of the commands for executors; 2) verifying the completeness of executors; 3) enhancing the security (e.g., the protection of users' privacy). We further propose and compare two paradigms for implementing the first two capabilities. One is to leverage the generic knowledge of LLMs themselves via prompt engineering while the other is to adopt domain-specific learnable models. Moreover, we introduce a local memory mechanism for achieving the third capability. We evaluate our proposed ResponsibleTA on UI task automation and hope it could bring more attentions to ensuring LLMs more responsible in diverse scenarios. The research project homepage is at https://task-automation-research.github.io/responsible_task_automation.