{"total":29,"rows":[{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40,"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":"2512.18880","title":"Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction","created":"2025-12-21","cited_by_count":7,"area":null},{"id":"2411.15560","title":"Do LLMs Agree on the Creativity Evaluation of Alternative Uses?","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2508.08314","title":"Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2601.09953","title":"Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2507.05890","title":"Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2507.08232","title":"Can LLMs Reliably Simulate Real Students' Abilities in Mathematics and Reading Comprehension?","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2606.18709","title":"LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2510.14966","title":"Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2606.15643","title":"Extending Item Response Theory for Efficient and Meaningful Multilingual Evaluation","created":"2026-06-14","cited_by_count":2,"area":null},{"id":"2506.08260","title":"Automatic Generation of Inference Making Questions for Reading Comprehension Assessments","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2511.05903","title":"The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2601.02580","title":"Reconstructing Item Characteristic Curves using Fine-Tuned Large Language Models","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2605.18562","title":"Estimating Item Difficulty with Large Language Models as Experts","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.19529","title":"Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2608.15630","title":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2411.00045","title":"A Novel Psychometrics-Based Approach to Developing Professional Competency Benchmark for Large Language Models","created":"2024-10-29","cited_by_count":0,"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":"2505.21997","title":"Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.13384","title":"Delving Into the Psychology of Machines: Exploring the Structure of Self-Regulated Learning via LLM-Generated Survey Responses","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2510.22170","title":"Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2511.07451","title":"Exploring the Psychometric Validity of AI-Generated Student Responses: A Study on Virtual Personas' Learning Motivation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2607.26317","title":"Aligning LLM-Simulated and Human Examinees for Psychometric Calibration: A Cognitive Diagnostic Profiling Approach","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.04554","title":"Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.07316","title":"Natural Language Processing Psychometrics","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.16893","title":"A Framework for Using and Evaluating LLMs as Surrogate Experts in Security Surveys: Reliability, Bias, and Implications","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.17810","title":"Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.24825","title":"A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}