Abstract
Large language models (LLMs) have been a catalyst for the increased use of AI for automatic item generation on high-stakes assessments. Standard human review processes applied to human-generated content are also important for AI-generated content because AI-generated content can reflect human biases. However, human reviewers have implicit biases and gaps in cultural knowledge which may emerge where the test population is diverse. Quantitative analyses of item responses via differential item functioning (DIF) can help to identify these unknown biases. In this paper, we present DIF results based on item responses from a high-stakes English language assessment (Duolingo English Test - DET). We find that human- and AI-generated content, both of which were reviewed for fairness and bias by humans, show similar amounts of DIF overall but varying amounts by certain test-taker groups. This finding suggests that humans are unable to identify all biases beforehand, regardless of how item content is generated. To mitigate this problem, we recommend that assessment developers employ human reviewers which represent the diversity of the test-taking population. This practice may lead to more equitable use of AI in high-stakes educational assessment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Test-taker operating system is a proxy for socioeconomic status (SES), with Mac correlating to higher SES.
- 2.
This definition describes “intercept DIF” but not “slope DIF”. We focus on evaluating intercept DIF here to simplify the presentation of results. See Millsap [10] for a more general definition of DIF.
- 3.
A score of .5 means that half of the damaged words in the passage were completed correctly.
References
Gierl, M.J., Haladyna, T.M. (eds.): Automatic Item Generation: Theory and Practice. Routledge, Abingdon (2012)
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. (CSUR) 54(6), 1–35 (2021)
Zieky, M.J.: Fairness in test design and development. In: Dorans, N.J., Cook, L.L. (eds.) Fairness in Educational Assessment and Measurement, pp. 9–31. Routledge (2016)
Zieky, M.J.: Developing fair tests. In: Downing, S.M., Haladyna, T.M. (eds.) Handbook of Test Development, pp. 97–115. Routledge (2015)
Sherman, J.E.: Multiple levels of cultural bias in TESOL course books. RELC J. 41(3), 267–281 (2010)
Brown, T., et al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877–1901 (2020)
Cardwell, R., Naismith, B., LaFlair, G.T., Nydick, S.W.: Duolingo English Test: Technical Manual [Duolingo Research Report]. Duolingo (2023). https://go.duolingo.com/dettechnicalmanual
Council of Europe: Common European Framework of Reference for Languages: Learning, Teaching, Assessment. Press Syndicate of the University of Cambridge, UK (2001)
Attali, Y., et al.: The interactive reading task: transformer-based automatic item generation. Front. Artif. Intell. 5, 903077 (2022)
Millsap, R.E.: Statistical Approaches to Measurement Invariance. Routledge, Abingdon (2011)
Swaminathan, H., Rogers, H.J.: Detecting differential item functioning using logistic regression procedures. J. Educ. Meas. 27(4), 361–370 (1990)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Belzak, W.C.M., Naismith, B., Burstein, J. (2023). Ensuring Fairness of Human- and AI-Generated Test Items. In: Wang, N., Rebolledo-Mendez, G., Dimitrova, V., Matsuda, N., Santos, O.C. (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky. AIED 2023. Communications in Computer and Information Science, vol 1831. Springer, Cham. https://doi.org/10.1007/978-3-031-36336-8_108
Download citation
DOI: https://doi.org/10.1007/978-3-031-36336-8_108
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36335-1
Online ISBN: 978-3-031-36336-8
eBook Packages: Computer ScienceComputer Science (R0)