Finding Words Associated with DIF: Predicting Differential Item Functioning using LLMs and Explainable AI
This research addresses fairness in educational assessments by providing a tool to screen and revise items, particularly benefiting resource-limited programs and small subpopulations, though it is incremental as it applies existing methods to a new domain.
The study tackled predicting differential item functioning (DIF) from item text using fine-tuned Transformer LLMs and explainable AI, achieving prediction R² values from 0.04 to 0.32 across group pairs, and found that DIF-associated words often relate to test blueprint sub-domains rather than irrelevant content.
We fine-tuned and compared several encoder-based Transformer large language models (LLM) to predict differential item functioning (DIF) from the item text. We then applied explainable artificial intelligence (XAI) methods to these models to identify specific words associated with DIF. The data included 42,180 items designed for English language arts and mathematics summative state assessments among students in grades 3 to 11. Prediction $R^2$ ranged from .04 to .32 among eight focal and reference group pairs. Our findings suggest that many words associated with DIF reflect minor sub-domains included in the test blueprint by design, rather than construct-irrelevant item content that should be removed from assessments. This may explain why qualitative reviews of DIF items often yield confusing or inconclusive results. Our approach can be used to screen words associated with DIF during the item-writing process for immediate revision, or help review traditional DIF analysis results by highlighting key words in the text. Extensions of this research can enhance the fairness of assessment programs, especially those that lack resources to build high-quality items, and among smaller subpopulations where we do not have sufficient sample sizes for traditional DIF analyses.