对齐目标问题：人类、人工智能系统及其设计者的道德判断分歧
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
AI总结：
研究探讨了人类、AI系统及其设计者在道德判断上的差异，通过实验发现人类设计的AI行为会引发更强烈的道德约束，揭示了价值对齐的挑战。
摘要：
将机器行为与人类价值观对齐的项目面临一个基本问题：应由谁的道德期望指导AI决策？许多对齐研究假设适当的基准是人类自身在特定情境下的行为。针对代理类型价值分歧的研究挑战这一假设，显示人们并不总是对人类和AI系统做出相同判断。本文进一步挑战这一假设，探讨两种可能性：首先，当AI的人类起源变得明显时，对AI行为的评估会变化；其次，人们对编程AI系统的设计师的判断与被比较的机器或人类行为者不同。一项涉及1002名美国成年人的实验测量了 runaway mine train 情境中的道德判断，通过四个条件变化评估对象：维修工、维修机器人、由公司工程师编程的维修机器人，以及工程师编程维修机器人。发现维修工和机器人评估无显著差异。然而，当机器人行为被描述为人类设计的产物时，判断明显变化。参与者在评估编程机器人或其程序员时表现出更明显的义务论、规则导向的推理，表明揭示人类代理性会激活更高的道德约束。这些发现表明，人们可能对人类、在相同情境中行动的AI系统以及其设计者进行截然不同的评估。这些评估不一定收敛，引发了对齐目标问题：在高风险领域开发人工道德代理时，应以何种规范目标指导，以及这些多元判断能否在价值对齐的统一框架内得到调和。
英文摘要：
The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act in a given situation. Studies of agent-type value forks challenge this assumption by showing that people do not always judge humans and AI systems identically. This paper extends that challenge by examining two further possibilities: first, that evaluations of AI behavior change when its human origins are made visible; and second, that people judge the humans who program AI systems differently from either the machines or the human actors they are compared against. An experiment with 1,002 U.S. adults measured moral judgments in a runaway mine train scenario, varying the subject of evaluation across four conditions: a repairman, a repair robot, a repair robot programmed by company engineers, and company engineers programming a repair robot. We find no significant difference in evaluations of the repairman and the robot. However, judgments shifted substantially when the robot's actions were described as the product of human design. Participants exhibited markedly more deontological, rule-based reasoning when evaluating either the programmed robot or the engineers who programmed it, suggesting that rendering human agency visible activates heightened moral constraints. These findings indicate that people may evaluate humans, AI systems acting in the same situation, and the humans who design them in meaningfully different ways. The fact that these evaluations do not necessarily converge gives rise to the alignment target problem: which normative target should guide the development of artificial moral agents in high-stakes domains, and whether these plural judgments can be reconciled within a coherent account of value alignment.
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。
