[论文解读] Making AI Intelligible: Philosophical Foundations

Herman Cappelen, Joshua Dever|arXiv (Cornell University)|Jun 12, 2024

Ethics and Social Impacts of AI被引用 7

一句话总结

本文认为外部主义的意义哲学可以建模并改善人类与AI的理解与沟通，并概述以关于意义的形而上学理论为基础的可解释AI的步骤。

ABSTRACT

Can humans and artificial intelligences share concepts and communicate? 'Making AI Intelligible' shows that philosophical work on the metaphysics of meaning can help answer these questions. Herman Cappelen and Josh Dever use the externalist tradition in philosophy to create models of how AIs and humans can understand each other. In doing so, they illustrate ways in which that philosophical tradition can be improved. The questions addressed in the book are not only theoretically interesting, but the answers have pressing practical implications. Many important decisions about human life are now influenced by AI. In giving that power to AI, we presuppose that AIs can track features of the world that we care about (for example, creditworthiness, recidivism, cancer, and combatants). If AIs can share our concepts, that will go some way towards justifying this reliance on AI. This ground-breaking study offers insight into how to take some first steps towards achieving Interpretable AI.

研究动机与目标

• 激励 AI 如何共享并跟踪对人类重要的世界特征（例如信用状况、癌症、再犯率）。
• 展示外部主义意义理论如何建模人类–AI 的理解与沟通。
• 阐明构建可解释 AI 系统的实际影响。

提出的方法

• 考察关于意义的形而上学的外部主义哲学传统。
• 基于共享概念发展跨物种（人类–AI）理解的模型。
• 分析如何完善哲学以支持 AI 的可解释性。

实验结果

研究问题

• RQ1 人类与人工智能是否能够共享概念并进行有效沟通？
• RQ2 外部主义意义理论如何为 AI 理解与可解释性模型提供信息？
• RQ3 从哲学基础出发推进可解释 AI 的实际步骤有哪些？

主要发现

• 外部主义意义理论可以为人类–AI 理解的模型提供信息。
• 哲学基础为在重要人生决策中依赖 AI 提供了合理性路径。
• 将 AI 可解释性与哲学结合可以为迈向可解释 AI 的第一步提供指导。