Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge

TL;DR

This paper argues that evaluating generative AI systems is a complex social science measurement challenge that requires rigorous, theory-based approaches to improve validity and stakeholder participation.

Contribution

It introduces a four-level social science measurement framework for assessing GenAI capabilities, behaviors, and impacts, enhancing evaluation rigor and inclusivity.

Findings

Framework broadens stakeholder involvement

Enhances validity of evaluation methods

Bridges AI evaluation with social science principles

Abstract

The measurement tasks involved in evaluating generative AI (GenAI) systems lack sufficient scientific rigor, leading to what has been described as "a tangle of sloppy tests [and] apples-to-oranges comparisons" (Roose, 2024). In this position paper, we argue that the ML community would benefit from learning from and drawing on the social sciences when developing and using measurement instruments for evaluating GenAI systems. Specifically, our position is that evaluating GenAI systems is a social science measurement challenge. We present a four-level framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, behaviors, and impacts of GenAI systems. This framework has two important implications: First, it can broaden the expertise involved in evaluating GenAI systems by enabling stakeholders with different perspectives to participate in conceptual debates. Second, it brings rigor to both conceptual and operational debates by offering a set of lenses for interrogating validity.