NCME Annual Meeting 2026 - AI Talks
Wednesday - 8th of April
| Time | Title | Presenter(s) | Place |
|---|---|---|---|
| 8:00 - 10:00 | Using LLMs for Scalable, Auditable Qualitative Coding & Scoring in Google Sheets | Max Lu and Rony Rodriguez-Ramirez | Silver Lake B |
| 10:00-12:00 | Applying Data Mining in Multi-Agent Systems for Test Fraud Detection | Kaiwen Man, Sarah Toton, Kylie Gorney, Jujia Li, Qipeng Chen | Hollywood Ballroom I |
| 10:00-12:00 | Bayesian Networks in the Age of AI (A Tribute to Robert Mislevy) | Duanli Yan, Diego Zapata-Rivera, and Russell Almond | Hollywood Ballroom II |
| 10:00-12:00 | Demystify Amazon Web Services (AWS): Cloud Computing and Artificial Intelligence in Psychometric Applications | Ye Ma, Vinita Talreja, Mingqin Zhang, and Huiijuan Meng | Wilshire Grand Ballroom I |
| 10:00-12:00 | Integrating Generative AI into R Workflows: From APIs to Shiny Apps | Chris Runyon | Wilshire Grand Ballroom III |
| 1:00-5:00 | Beyond the Score: Creating Rich Feedback with Digital Assessment Data and AI | Hongwen Guo, Matthew Johnson, Luis Saldivia, and Michelle Worthington | Wilshire Grand Ballroom I |
Thursday - 9th of April
| Time | Title | Place |
|---|---|---|
| 7:45-9:15 | Item Parameter Prediction and Difficulty Modeling | Silver Lake A |
| 7:45-9:15 | Three Years After GPT-4: How Has AI Changed Assessments? How Will It? | Westwood |
| 9:45-11:15 | Evaluating the Effectiveness of AI | K-Town |
| 9:45-11:15 | Automated Scoring Engine Training: Addressing Real World Constraints | Roosevelt A |
| 9:45-11:15 | Individual eBoards: AI, Technology, and CAT | Hancock Park |
| 11:30-12:30 | Individual eBoards: AI and Automated Scoring | Hancock Park |
| 11:30-12:45 | AI in Medical Assessment: Innovations in Content, Credibility, and Classification | Roosevelt A |
| 11:30-12:45 | The Design Dialog: How AI Amplifies and Needs Assessment Design Frameworks | Roosevelt B |
| 11:30-12:45 | Deconstructing AI Outputs for Bias in the Workplace | Boyle Heights |
| 11:30-1:00 | Using AI for Aligning Standards | Hollywood Ballroom II |
| 1:45-3:15 | Assessing Invariance of Automated Scoring Models | K-Town |
| 1:45-3:15 | AI Ethics, Policy, and Practice in Training Measurement Professionals: A Panel Discussion | Roosevelt A |
| 3:45-5:15 | Applications of AI in Psychometrics and Assessment | K-Town |
| 3:45-5:15 | From Topic Models to LLMs: AI-Driven Applications in Educational Measurement | Roosevelt B |
Friday - 10th of April
| Time | Title | Place |
|---|---|---|
| 9:45-11:15 | From Generation to Calibration: Leveraging AI for Item Development, Piloting, and Scoring | Hollywood Ballroom II |
| 9:45-11:15 | Advancing Conversation-Based Assessment with Large Language Models | Roosevelt B |
| 11:30-12:45 | Integrating AI into Assessment and Psychometric Practice | Silver Lake |
| 11:30-12:45 | Measurement-Informed Approaches to Evaluate GenAI Outputs (AIME Session) | Wilshire Grand Ballroom III |
| 1:45-3:00 | Advances in Scoring English Language Learner Items and Responses | Roosevelt A |
| 1:45-3:00 | Automated Coding with LLM: Accuracy and Fairness | Silver Lake B |
| 3:30-5:00 | Practical Applications of Artificial Intelligence in the Development of Large-Scale Assessments | Hollywood Ballroom II |
| 3:30-5:00 | Creating and Evaluating Automated Raters | Majestic |
Saturday - 11th of April
| Time | Title | Place |
|---|---|---|
| 7:45-9:15 | Scoring Early Literacy Tasks: Cross-Vendor Research and Perspectives | Majestic |
| 8:30-9:45 | Graduate Student eBoards: AI & Machine Learning | Hancock Park |
| 9:45-11:15 | AI Item Difficulty Modeling | Boyle Heights |
| 9:45-11:15 | AI-Assisted Assessment Development | K-Town |
| 9:45-11:15 | Automated Scoring Research: Security, Efficiency, and Interpretability | Ladera Heights |
| 9:45-11:15 | AI, Machine Learning, & Natural Language Processing Research | Roosevelt B |
| 11:30-12:45 | AI-Driven Interactive Speaking and Math Assessments: Innovations in Design and Scoring | Ladera Heights |
| 11:30-12:45 | An NCME Debate Session: The AI Landscape for Industry and Academia | Wilshire Grand Ballroom III |
| 1:45-3:15 | Fairness Concerns with AI | Roosevelt B |
| 1:45-3:15 | Psychometric Overlord Auditions Take 2: Prove Me Wrong | Hollywood Ballroom II |
| 3:30-5:00 | Text/Speech-based Approaches to Item Parameter Modeling | Boyle Heights |
| 3:30-5:00 | Automated Scoring: Combining and Comparing Human and AI Raters | Roosevelt A |
| 3:30-5:00 | Inclusion, Equity, and Fairness in TIMSS and PIRLS | Westwood |
