Measuring Error Alignment for Decision-Making Systems
This work addresses the problem of ensuring AI systems align with human values for decision-making applications, offering incremental improvements in behavioral alignment methods.
The paper tackles the challenge of assessing AI system trustworthiness by proposing two new behavioral alignment metrics—misclassification agreement and class-level error similarity—that measure error similarities between AI and human systems, showing they correlate well with representational alignment metrics and provide complementary information across various domains.
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.