{"total":19,"rows":[{"id":"2405.11591","title":"Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation","created":"2024-05-19","cited_by_count":58,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2404.17460","title":"Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System","created":"2024-04-26","cited_by_count":26,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2405.05253","title":"Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge","created":"2024-05-08","cited_by_count":20,"area":null},{"id":"2310.01420","title":"Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2405.20529","title":"An Automatic Question Usability Evaluation Toolkit","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2410.16547","title":"PromptHive: Bringing Subject Matter Experts Back to the Forefront with Collaborative Prompt Engineering for Educational Content Creation","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2403.14443","title":"Language Models Can Reduce Asymmetry in Information Markets","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2409.07453","title":"\"My Grade is Wrong!\": A Contestable AI Framework for Interactive Feedback in Evaluating Student Essays","created":"2024-09-11","cited_by_count":5,"area":null},{"id":"2602.06221","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2404.11072","title":"Large Language Models Meet User Interfaces: The Case of Provisioning Feedback","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2406.12381","title":"QOG:Question and Options Generation based on Language Model","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2503.10533","title":"The Impact of Item-Writing Flaws on Difficulty and Discrimination in Item Response Theory","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2509.15059","title":"QuizRank: Picking Images by Quizzing VLMs","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2512.15006","title":"Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2608.21106","title":"Atom Learning Model (ALM): how a real classroom got tokenised","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.26087","title":"The Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at Scale","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.04267","title":"AI-Enabled Quality Assurance for Multiple-Choice Assessment Items","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}