用计算理论框架分析人机协同系统，揭示责任归属与可解释性的根本矛盾。
Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility
- 用预言机理论区分三类人机协同模式：监控、单次干预、深度交互
- 发现不同模式下法律安全性和失效风险差异显著，部分设计易失控
- 指出现行英欧法律忽视实际技术限制，需调整责任认定机制
本文利用可计算性理论中的预言机和归约概念，形式化了人工智能系统中人类在环路（HITL）的不同设置，区分了单纯的人员监控（即全函数）、单点人类操作（即多对一归约）以及高度互动的人机协作（即图灵归约）。随后表明，不同设置下的法律地位与安全性存在显著差异。本文提出一个分类体系以归纳HITL的失效模式，强调其实际应用中的局限性。研究揭示英国与欧盟现行法律框架存在疏漏，过度聚焦某些可能无法实现预期伦理、法律和社会技术目标的HITL设置。我们建议法律应承认不同设置的有效性，并在相应情境中合理分配责任，避免将问题归咎于人类。整体上，研究揭示了法律责任归属与技术可解释性之间不可避免的权衡。结果表明，HITL设置涉及多重技术设计决策，且可能因超出人类控制的原因而失效。本研究提出的形式化框架与分类体系为理解构建有效人机协同系统的挑战提供了新的分析视角，有助于开发者与立法者优化设计以达成预期目标。
原文摘要 · Abstract (English)
We use the notion of oracle machines and reductions from computability theory to formalise different Human-in-the-loop (HITL) setups for AI systems, distinguishing between trivial human monitoring (i.e., total functions), single endpoint human action (i.e., many-one reductions), and highly involved human-AI interaction (i.e., Turing reductions). We then proceed to show that the legal status and safety of different setups vary greatly. We present a taxonomy to categorise HITL failure modes, highlighting the practical limitations of HITL setups. We then identify omissions in UK and EU legal frameworks, which focus on HITL setups that may not always achieve the desired ethical, legal, and sociotechnical outcomes. We suggest areas where the law should recognise the effectiveness of different HITL setups and assign responsibility in these contexts, avoiding human "scapegoating". Our work shows an unavoidable trade-off between attribution of legal responsibility, and technical explainability. Overall, we show how HITL setups involve many technical design decisions, and can be prone to failures out of the humans' control. Our formalisation and taxonomy opens up a new analytic perspective on the challenges in creating HITL setups, helping inform AI developers and lawmakers on designing HITL setups to better achieve their desired outcomes.
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。