Validity Arguments For Constructed Response Scoring Using Generative Artificial Intelligence Applications

TL;DR

This paper examines the validity of using generative AI for scoring constructed responses, comparing it to traditional and feature-based methods, and proposes best practices for validity evidence collection.

Contribution

It highlights the differences in validity evidence requirements for generative AI scoring systems and offers guidelines for supporting score validity in high-stakes testing.

Findings

Generative AI scoring requires more extensive validity evidence than feature-based NLP.

Constructed response scores from AI can be validated using multiple evidence sources.

Combining AI scores from different sources may improve construct coverage.

Abstract

The rapid advancements in large language models and generative artificial intelligence (AI) capabilities are making their broad application in the high-stakes testing context more likely. Use of generative AI in the scoring of constructed responses is particularly appealing because it reduces the effort required for handcrafting features in traditional AI scoring and might even outperform those methods. The purpose of this paper is to highlight the differences in the feature-based and generative AI applications in constructed response scoring systems and propose a set of best practices for the collection of validity evidence to support the use and interpretation of constructed response scores from scoring systems using generative AI. We compare the validity evidence needed in scoring systems using human ratings, feature-based natural language processing AI scoring engines, and generative AI. The evidence needed in the generative AI context is more extensive than in the feature-based NLP scoring context because of the lack of transparency and other concerns unique to generative AI such as consistency. Constructed response score data from standardized tests demonstrate the collection of validity evidence for different types of scoring systems and highlights the numerous complexities and considerations when making a validity argument for these scores. In addition, we discuss how the evaluation of AI scores might include a consideration of how a contributory scoring approach combining multiple AI scores (from different sources) will cover more of the construct in the absence of human ratings.