衡量决策系统的错误对齐
Measuring Error Alignment for Decision-Making Systems
AI总结：
本文针对AI决策系统与人类价值观对齐问题，提出误分类一致性和类别级错误相似性两个行为对齐指标，验证其与表征对齐指标的相关性及互补价值。
摘要：
鉴于人工智能系统将在未来的决策过程中发挥关键作用，其可信度和可靠性成为至关重要的关注点。由于其规模和复杂性，现代人工智能系统难以直接解释，因此需要替代方法来建立对这些系统的信任，并确定它们与人类价值观的对齐程度。我们认为，衡量人工智能与人类之间信息处理相似性的良好指标，或许能够实现这些目标。虽然表征对齐（Representational alignment，RA）方法衡量两个系统内部状态之间的相似性，但相关数据对于人类系统而言可能昂贵且难以收集。相比之下，行为对齐（Behavioural alignment，BA）比较更便宜、更容易，但其敏感性和可靠性仍存疑问。我们提出了两个新的行为对齐指标：误分类一致性（misclassification agreement），用于衡量两个系统在相同实例上错误之间的相似性；以及类别级错误相似性（class-level error similarity），用于衡量两个系统错误分布之间的相似性。我们表明，在一系列领域中，我们的指标与RA指标具有良好的相关性，并为另一个BA指标提供了互补信息，从而为一种新的价值对齐方法奠定了基础。
英文摘要：
Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and alternative ways are needed to establish trust in those systems, and determine how well they align with human values. We argue that good measures of the information processing similarities between AI and humans, may be able to achieve these same ends. While Representational alignment (RA) approaches measure similarity between the internal states of two systems, the associated data can be expensive and difficult to collect for human systems. In contrast, Behavioural alignment (BA) comparisons are cheaper and easier, but questions remain as to their sensitivity and reliability. We propose two new behavioural alignment metrics misclassification agreement which measures the similarity between the errors of two systems on the same instances, and class-level error similarity which measures the similarity between the error distributions of two systems. We show that our metrics correlate well with RA metrics, and provide complementary information to another BA metric, within a range of domains, and set the scene for a new approach to value alignment.
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。
