arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.11705cs.AIcs.CY
收藏

认真对待原则:价值对齐的混合方法

Taking Principles Seriously: A Hybrid Approach to Value Alignment

Carnegie Mellon University(卡内基梅隆大学);University of Pennsylvania(宾夕法尼亚大学)

Tae Wan Kim, John Hooker, Thomas Donaldson

摘要:

在人工智能中开发价值对齐(VA)系统的重要一步是理解VA如何反映有效的道德原则。我们建议,设计师的VA系统纳入道德利用混合的方法,其中道德推理和经验观察发挥作用。我们认为,这避免了犯下“自然主义谬误”,这是一种试图从“是”中推导出“应该”的尝试,而且当不犯下这种谬误时,它提供了一种更适当的伦理推理形式。使用量化的模型逻辑,我们精确地制定原则来自道义伦理学,并显示它们如何意味着特定的“测试命题”的任何给定的行动计划,在人工智能规则库。只有当测试命题在经验上是真实的,即基于经验VA做出的判断时,行动计划才是道德的。这使得经验VA无缝整合独立合理的伦理原则。

英文摘要:

An important step in the development of value alignment (VA) systems in AI is understanding how VA can reflect valid ethical principles. We propose that designers of VA systems incorporate ethics by utilizing a hybrid approach in which both ethical reasoning and empirical observation play a role. This, we argue, avoids committing the "naturalistic fallacy," which is an attempt to derive "ought" from "is," and it provides a more adequate form of ethical reasoning when the fallacy is not committed. Using quantified model logic, we precisely formulate principles derived from deontological ethics and show how they imply particular "test propositions" for any given action plan in an AI rule base. The action plan is ethical only if the test proposition is empirically true, a judgment that is made on the basis of empirical VA. This permits empirical VA to integrate seamlessly with independently justified ethical principles.

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。

↑