Developing valid assessments in the era of generative artificial intelligence
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Generative Artificial Intelligence (GAI) holds tremendous potential to transform the field of education because GAI models can consider context and therefore can be trained to deliver quick and meaningful evaluation of student learning outcomes. However, current versions of GAI tools have considerable limitations, such as social biases often inherent in the data sets used to train the models. Moreover, the GAI revolution comes during a period of moving away from memorization-based education systems toward supporting learners in developing the ability to apply knowledge and skills to solve real-world problems and explain real-world phenomena. A challenge in using GAI tools for scoring assessments aimed at fostering knowledge application is ensuring that these algorithms are scoring the same construct attributes (e.g., knowledge and skills) as a trained human scorer would score when evaluating student performance. Similarly, if using GAI tools to develop assessments, one needs to ensure that the goals of GAI-generated assessments are aligned with the vision and performance expectations of the learning environments for which these assessments are developed. Currently, no guidelines have been identified for assessing the validity of AI-based assessments and assessment results. This paper represents a conceptual analysis of issues related to developing and validating GAI-based assessments and assessment results to guide the learning process. Our primary focus is to investigate how to meaningfully leverage capabilities of GAI for developing assessments. We propose ways to evaluate the validity evidence of GAI-produced assessments and assessment scores based on existing validation approaches. We discuss future research avenues aimed at establishing guidelines and methodologies for assessing the validity of AI-based assessments and assessment results. We ground our discussion in the theory of validity outlined in the Standards for Educational and Psychological Testing by the American Educational Research Association and discuss how we envision building on the standards for establishing the validity of inferences made from the test scores in the context of GAI-based assessments.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BAİDOO-ANU, D., & OWUSU ANSAH, L. (2023) · Journal of AI · doi:10.61969/jai.1337500 · Cited by 3,939
Baidoo-Anu, D., & Owusu Ansah, L. (2023) · doi:10.2139/ssrn.4337484 · Cited by 3,004
Generative AI tools and assessment: Guidelines of the world's top-ranking universities
Moorhouse, B. L., Yeo, M. A., & Wan, Y. (2023) · Computers and Education Open · doi:10.1016/j.caeo.2023.100151 · Cited by 461
Applying machine learning in science assessment: A systematic review
Zhai, X., Yin, Y., Pellegrino, J. W., Haudek, K. C., & Shi, L. (2020) · Studies in Science Education · doi:10.1080/03057267.2020.1735757 · Cited by 257
Cited by
Redesigning assessments for AI-enhanced learning: a framework for educators in the generative AI era
Khlaif, Z. N., Alkouk, W. A., Salama, N., & Abu Eideh, B. (2025) · Education Sciences · doi:10.3390/educsci15020174 · Cited by 127
“Future research should establish guidelines and methodologies for assessing AI-based assessments (Kaldaras et al., 2024).”
Agentic AI in Education: State of the Art and Future Directions
Kostopoulos, G., Gkamas, V., Rigou, M., & Kotsiantis, S. (2025) · IEEE Access · doi:10.1109/access.2025.3620473 · Cited by 69
Jovic, M., Papakonstantinidis, S., & Kirkpatrick, R. (2025) · Language Testing in Asia · doi:10.1186/s40468-025-00389-2 · Cited by 11
Kumar, A., Baijal, A., & Kharat, M. (2025) · Journal of International Education in Business · doi:10.1108/jieb-07-2024-0086 · Cited by 6
Lin, P., Deng, Q., & Zhou, Y. (2026) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2025.100534 · Cited by 4
Metadata
- Authors
- Kaldaras, L., Akaeze, H. O., & Reckase, M. D.
- Venue
- Frontiers in Education
- Publisher
- Frontiers Media SA
- Published
- 2024-08-07
- Volume
- 9
- ISSN
- 2504-284X (ISSN-L)
- OpenAlex
- W4401403953
- Cited by
- 58
- References
- 4
- FWCI
- 22.20
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.