Zhongzhou Chen

Naiming Liu, Leo Murch, Spencer Moore et al.

Traditional synchronous STEM assessments face growing challenges including accessibility barriers, security concerns from resource-sharing platforms, and limited comparability across institutions. We present a framework for generating and evaluating large-scale isomorphic physics problem banks using Generative AI to enable asynchronous, multi-attempt assessments. Isomorphic problems test identical concepts through varied surface features and contexts, providing richer variation than conventional parameterized questions while maintaining consistent difficulty. Our generation framework employs prompt chaining and tool use to achieve precise control over structural variations (numeric values, spatial relations) alongside diverse contextual variations. For pre-deployment validation, we evaluate generated items using 17 open-source language models (LMs) (0.6B-32B) and compare against actual student performance (N>200) across three midterm exams. Results show that 73% of deployed banks achieve statistically homogeneous difficulty, and LMs pattern correlate strongly with student performance (Pearson's $ρ$ up to 0.594). Additionally, LMs successfully identify problematic variants, such as ambiguous problem texts. Model scale also proves critical for effective validation, where extremely small (<4B) and large (>14B) models exhibit floor and ceiling effects respectively, making mid-sized models optimal for detecting difficulty outliers.

Yizhu Gao, Zhongzhou Chen, Min Li et al.

Generative Artificial Intelligence (GenAI) presents a governance challenge for STEM assessment. Unrestricted GenAI access enables task outsourcing that undermines the validity of traditional assessments; blanket prohibitions are difficult to enforce, may push use underground, and do little to prepare students for workplaces where GenAI-supported workflows are increasingly common. This paper addresses this dilemma by proposing a framework grounded in Evidence-Centered Design (ECD) that treats GenAI as a design variable within the assessment argument rather than an external threat to it. The framework analyzes how GenAI reshapes the student model, evidence model, and task model, and uses this analysis to articulate three principled governance stances. Restrict is warranted when GenAI would contaminate the inferential link between student work products and targeted unaided proficiency. Scaffold is warranted when bounded GenAI support can support peripheral demands without revealing the target construct, preserving inferential interpretability. Require is warranted when the target construct is disciplinary AI interaction competency and tasks can be designed to elicit process artifacts, including prompts, critiques, and revisions, that make student reasoning observable, scorable, and distinguishable from AI-generated output. This framework specifies when to restrict, scaffold, or require GenAI use in STEM assessment. We present two task designs deployed in an introductory physics course and demonstrate that disciplinary AI interaction competencies are observable in student response artifacts and can be scored using defensible rubrics grounded in student data and expert knowledge. By situating GenAI governance within validity arguments, the framework offers actionable guidance for preserving learning integrity while supporting authentic preparation for AI-enabled professional environments.

Robinson Ferrer, Damla Turgut, Zhongzhou Chen et al.

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be correct}. This enables selective automation where high-confidence predictions are processed automatically while uncertain cases are flagged for human review. We compare three confidence estimation methods (self-reported confidence, self-consistency voting, and token probability) across seven LLMs of varying scale (4B to 120B parameters) on three educational datasets: RiceChem (long-answer chemistry), SciEntsBank, and Beetle (short-answer science). Our experiments reveal that self-reported confidence consistently achieves the best calibration across all conditions (avg ECE 0.166 vs 0.229 for self-consistency). Surprisingly, self-consistency remains 38\% worse despite requiring 5$\times$ the inference cost. Larger models exhibit substantially better calibration though gains vary by dataset and method (e.g., a 28\% ECE reduction for self-reported), with GPT-OSS-120B achieving the best calibration (avg ECE 0.100) and strong discrimination (avg AUC 0.668). We also observe that confidence is strongly top-skewed across methods, creating a ``confidence floor'' that practitioners must account for when setting thresholds. These findings suggest that simply asking LLMs to report their confidence provides a practical approach for identifying reliable grading predictions. Code is available \href{https://github.com/sonkar-lab/llm_grading_calibration}{here}.

Zhongzhou Chen

We present a method for generating large numbers of isomorphic physics problems using generative AI services such as ChatGPT, through prompt chaining and tool use. This approach enables precise control over structural variations-such as numeric values and spatial relations-while supporting diverse contextual variations in the problem body. By utilizing the Python code interpreter, the method supports automatic solution validation and simple diagram generation, addressing key limitations in existing LLM-based methods. We generated two example isomorphic problem banks and compared the outcome against two simpler prompt-based approaches. Results show that prompt-chaining produces significantly higher quality and more consistent outputs than simpler, non-chaining prompts. We also show that GenAI services can be used to validate the quality of the generated isomorphic problems. This work demonstrates a promising method for efficient and scalable problem creation accessible to the average instructor, which opens new possibilities for personalized adaptive testing and automated content development.