让AI像人一样思考，才能让人真正信任并依赖它。
Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
- 提出认知对齐：AI推理方式需与人类一致
- 调查显示多数用户认为推理对齐至关重要
- 适合高风险决策场景的AI系统研发者
AI系统正被广泛用于辅助决策、委托决策或自主决策。本文主张，在许多场景中，尤其是高风险决策，我们需要认知对齐的AI系统，使其推理方式与用户相似，并能真实传达其推理过程。我们回顾证据表明，认知对齐可提升可理解性与可信度，并提供新调查数据，显示许多用户认为当AI的判断依据重要时，认知对齐是‘必要’的。文章指出当前对齐方法与实现认知对齐之间的差距，并提出研究议程。我们认为，认知错位可能是众多设想应用中AI采纳的主要障碍，解决这一问题对构建用户愿意且有理由信赖的AI系统至关重要。
原文摘要 · Abstract (English)
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. 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. 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.
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。