原则不自行应用:一种诠释学视角下的人工智能对齐
Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment
AI总结:
本文从诠释学角度探讨AI对齐问题,指出原则应用需依赖情境判断,强调对齐过程中的解释性成分,并指出部署响应分布与语料库分布差异可能导致审计失效。
摘要:
AI对齐通常被描述为确保AI系统遵循陈述原则或人类偏好,但一般原则很少自行决定其在具体案例中的应用。当原则冲突、过于宽泛或相关事实不明确时,需要额外的判断步骤。本文通过诠释学视角分析这一步骤,认为对齐包含解释性成分:涉及情境敏感的判断,即如何解读、应用和优先处理原则。我们连接这一主张到近期实证发现,显示大量偏好标注数据处于原则冲突或不明确的情况,其中原则集无法唯一决定决策。我们进一步得出操作性结论:因为这些判断体现在行为上,许多与对齐相关的选择仅在部署时模型生成的响应分布中出现。为正式化这一观点,我们区分部署诱导和语料库诱导评估,并展示当两种响应分布不同时,非策略审计可能无法捕捉与对齐相关的失败。我们主张,基于原则的对齐包含情境依赖的解释性成分。
英文摘要:
AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when they are too broad to settle a situation, or when the relevant facts are unclear, an additional act of judgment is required. This paper analyzes that step through the lens of hermeneutics and argues that alignment therefore includes an interpretive component: it involves context-sensitive judgments about how principles should be read, applied, and prioritized in practice. We connect this claim to recent empirical findings showing that a substantial portion of preference-labeling data falls into cases of principle conflict or indifference, where the principle set does not uniquely determine a decision. We then draw an operational consequence: because such judgments are expressed in behavior, many alignment-relevant choices appear only in the distribution of responses a model generates at deployment time. To formalize this point, we distinguish deployment-induced and corpus-induced evaluation and show that off-policy audits can fail to capture alignment-relevant failures when the two response distributions differ. We argue that principle-specified alignment includes a context-dependent interpretive component.
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。