arXiv:2507.02582cs.AI2025-07被引 1

揭示集体决策中责任扩散与责任空白的计算复杂性边界

Responsibility Gap and Diffusion in Sequential Decision-Making Mechanisms

  • 从计算复杂性角度分析责任扩散与责任空白问题
  • 证明无责任扩散机制为Π₂完全,无责任空白机制为Π₃完全
  • 适合关注AI伦理与形式化推理的研究者

责任长期是法学与哲学的研究主题。近年来,其也成为人工智能领域的关注焦点。本文研究集体决策中两个关键责任属性——责任扩散与责任空白——的计算复杂性。结果表明,无责任扩散的决策机制集合属于Π₂-完全,无责任空白的决策机制集合属于Π₃-完全。同时,这两类机制的交集仍为Π₂-完全。

原文摘要 · Abstract (English)

Responsibility has long been a subject of study in law and philosophy. More recently, it became a focus of AI literature. The article investigates the computational complexity of two important properties of responsibility in collective decision-making: diffusion and gap. It shows that the sets of diffusion-free and gap-free decision-making mechanisms are $Π_2$-complete and $Π_3$-complete, respectively. At the same time, the intersection of these classes is $Π_2$-complete.

责任机制计算复杂性决策模型

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。