让智能机器在合理情况下拒绝用户指令，同时保障安全与责任可追溯。
Towards Responsibly Non-Compliant Machines
- 基于拒绝对话理由设计负责任的不执行机制
- 提供绕过拒绝的合法路径以避免系统僵局
- 关注安全风险与责任转移，适合伦理合规研究者
我们探讨如何构建能够负责任地拒绝用户请求的自主智能体。机器的不合规行为存在多种形式，需在任务拒绝的理由、违规行为的纠正路径、以及安全风险和责任转移等方面进行深入研究。本文提出应从正当性解释、可控干预机制和风险追踪三方面构建负责任的非合规能力，以确保智能系统在复杂场景下的安全与可信运行。
原文摘要 · Abstract (English)
We consider the problem of engineering autonomous intelligent agents that are capable to responsibly not comply with user requests. We argue that machine non-compliance comes in many different forms, and sketch the issues we should pursue on the road of accomplishing responsibly non-compliant intelligent machines. We anchor responsible non-compliance in justifications for task refusal, pathways to override the non-compliance, as well as careful tracking of security risks and liability transfers.
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。