Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning

立场：我们需要实用的 AI 对齐方法来模拟人类推理

Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes decision-making, we need accurate cognitively-aligned AI systems that reason similarly to their users, and faithfully communicate their reasoning.

摘要： 人工智能系统正越来越多地被用作决策辅助、决策代理或自主决策者。本立场论文指出，在许多场景中，特别是在高风险决策领域，我们需要精确的“认知对齐”（cognitively-aligned）AI 系统，使其推理方式与用户相似，并能忠实地传达其推理过程。

We review evidence that cognitive alignment improves understandability and trustworthiness, and provide new survey data showing that many users find cognitive alignment “essential” when an AI’s rationale for a judgment or action is important to them.

我们回顾了相关证据，证明认知对齐能够提高系统的可理解性和可信度；同时，我们提供了新的调查数据，显示当 AI 对某项判断或行动的解释对用户至关重要时，许多用户认为认知对齐是“必不可少”的。

We outline the gaps between existing alignment methods and what is needed to achieve cognitive alignment, and present a research agenda to address these gaps. We argue that cognitive misalignment represents a likely impediment to AI adoption in many envisioned applications, and that addressing it is important for creating AI systems on which users are both willing and justified to rely.

我们概述了现有对齐方法与实现认知对齐所需目标之间的差距，并提出了解决这些差距的研究议程。我们认为，认知不对齐很可能是 AI 在许多预期应用中普及的障碍，解决这一问题对于构建用户既愿意依赖、又有充分理由去信任的 AI 系统至关重要。