Assessment Design in the AI Era: A Method for Identifying Items Functioning Differentially for Humans and Chatbots

2026-03-24

AI Summary

In the context of widespread large language model (LLM) deployment, traditional assessments may become invalid due to systematic differences between human and AI response behaviors. This study pioneers the extension of differential item functioning (DIF) analysis—a psychometric technique—into the domain of human–AI ability comparison. By integrating negative contrast analysis with item-total correlation-based discrimination methods, the work establishes a novel assessment design paradigm tailored for the AI era. Leveraging data from high school chemistry diagnostic tests and college entrance examinations, the proposed approach is empirically validated. Expert analyses further identify key task dimensions influencing AI performance, offering both theoretical grounding and practical pathways for developing next-generation educational assessments that are robust against AI misuse while ensuring fairness and validity.

Technology Category

• Humans and AI: AI for Accessibility
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Evaluation and Analysis

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The rapid adoption of large language models (LLMs) in education raises profound challenges for assessment design. To adapt assessments to the presence of LLM-based tools, it is crucial to characterize the strengths and weaknesses of LLMs in a generalizable, valid and reliable manner. However, current LLM evaluations often rely on descriptive statistics derived from benchmarks, and little research applies theory-grounded measurement methods to characterize LLM capabilities relative to human learners in ways that directly support assessment design. Here, by combining educational data mining and psychometric theory, we introduce a statistically principled approach for identifying items on which humans and LLMs show systematic response differences, pinpointing where assessments may be most vulnerable to AI misuse, and which task dimensions make problems particularly easy or difficult for generative AI. The method is based on Differential Item Functioning (DIF) analysis -- traditionally used to detect bias across demographic groups -- together with negative control analysis and item-total correlation discrimination analysis. It is evaluated on responses from human learners and six leading chatbots (ChatGPT-4o \& 5.2, Gemini 1.5 \& 3 Pro, Claude 3.5 \& 4.5 Sonnet) to two instruments: a high school chemistry diagnostic test and a university entrance exam. Subject-matter experts then analyzed DIF-flagged items to characterize task dimensions associated with chatbot over- or under-performance. Results show that DIF-informed analytics provide a robust framework for understanding where LLM and human capabilities diverge, and highlight their value for improving the design of valid, reliable, and fair assessment in the AI era.

Problem

• assessment design
• large language models
• differential item functioning
• AI misuse
• educational evaluation

Innovation

• Differential Item Functioning
• Large Language Models
• Assessment Design
• Educational Data Mining
• Psychometric Theory