Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress

Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor 2026-10 National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States text conference publication 979-8-9983004-1-7 aime-con-2026-wip https://aclanthology.org/2026.aimecon-wip.0/ A Cognitive Lab Study of Student AI Chatbot Use in Online Coursework Jinah Choi author Sonya Powers author Farzan Karimi-Malekabadi author Michelle Barrett author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 choi-etal-2026-cognitive https://aclanthology.org/2026.aimecon-wip.1/ 2026-10 1 8 A Preliminary Semantic Screen for IRT Local Dependence Qian Shen author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 shen-2026-preliminary https://aclanthology.org/2026.aimecon-wip.2/ 2026-10 9 16 Evaluating Multi-Phase and Granular Strategies for Evidence-Anchored Automated Scoring Alessia Marigo author Laura Wright author Linda Malkin author Xin Xie author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 marigo-etal-2026-evaluating https://aclanthology.org/2026.aimecon-wip.3/ 2026-10 17 23 Consensus without Accuracy: Investigating LLM’s Recovery of Item Difficulty Using Paired Comparisons Michael Leon Chrzan author Benjamin Domingue author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 chrzan-domingue-2026-consensus https://aclanthology.org/2026.aimecon-wip.4/ 2026-10 24 36 Implementing Generative AI Assessment Guidelines in a Mexican University Melchor Sánchez-Mendiola author Enrique Buzo-Casanova author Elibidú Ortega-Sánchez author Manuel García-Minjares author Adriana Cruz Juárez author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 sanchez-mendiola-etal-2026-implementing https://aclanthology.org/2026.aimecon-wip.5/ 2026-10 37 44 TRACE: Automated Multi-Granularity Analysis of Text Revision Yu Tian author Katerina Christhilf author Andrew Potter author Jessica Early author Steve Graham author Danielle McNamara author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 tian-etal-2026-trace https://aclanthology.org/2026.aimecon-wip.6/ 2026-10 45 51 Comparing θ Representation Strategies for Reconstructing Item Characteristic Curves Sungjin Nam author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 nam-2026-comparing https://aclanthology.org/2026.aimecon-wip.7/ 2026-10 52 56 Assessing Large Language Model Performance in Post-Certification-Examination Comment Categorization Huaping Sun author Kristin O’Brien author Colleen Burke Kave author David Shin author Qiao Lin author Jeffrey Marc Lyness author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 sun-etal-2026-assessing https://aclanthology.org/2026.aimecon-wip.8/ 2026-10 57 61 Rethinking Pilot Data: Evaluating LLM Synthetic Data for Scale Development Margarita Olivera-Aguilar author Samuel H Rikoon author Paul D Bailey author Michael B Kruse author Kamal Middlebrook author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 olivera-aguilar-etal-2026-rethinking https://aclanthology.org/2026.aimecon-wip.9/ 2026-10 62 68 Hierarchical Attention Network Architecture for Automated Response Time Prediction Wei Shuang Schneider author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 schneider-2026-hierarchical https://aclanthology.org/2026.aimecon-wip.10/ 2026-10 69 78 Beyond Agreement: Calibrating Automated Scoring to Human Judgment Using Control Scripts Mark Dulhunty author Alex Codoreanu author Nathan Zoanetti author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 dulhunty-etal-2026-beyond https://aclanthology.org/2026.aimecon-wip.11/ 2026-10 79 85 Human-in-the-Loop Gemini Item Generation for Large-Scale MCQ Banks Melchor Sánchez-Mendiola author Milton García-Lima author Elibidú Ortega-Sánchez author Manuel García-Minjares author Enrique Buzo-Casanova author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 sanchez-mendiola-etal-2026-human https://aclanthology.org/2026.aimecon-wip.12/ 2026-10 86 92 Score Comparability Limits with Common AES Validation Measures Tim Moses author Seongeun Kim author Nick Trout author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 moses-etal-2026-score https://aclanthology.org/2026.aimecon-wip.13/ 2026-10 93 99 Finding Evidence of Communication Behaviors using LLMs Tazin Afrin author Saed Rezayi author Janet Mee author Polina Harik author Le An Ha author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 afrin-etal-2026-finding https://aclanthology.org/2026.aimecon-wip.14/ 2026-10 100 103 Designing and Evaluating a Measurement-Oriented RAG Framework for ELL Writing Assessment Daeryong Seo author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 seo-2026-designing https://aclanthology.org/2026.aimecon-wip.15/ 2026-10 104 112 Automated Item Evaluation: Predicting Item Acceptance and Rejection using LLM-Generated Critiques Hotaka Maeda author Yikai Lu author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 maeda-lu-2026-automated https://aclanthology.org/2026.aimecon-wip.16/ 2026-10 113 129 Production-Ready Automated Item Generation in Educational Assessment: Integration with Operational Workflows Hotaka Maeda author Kargi Chauhan author Tharunya Chandrashekar author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 maeda-etal-2026-production https://aclanthology.org/2026.aimecon-wip.17/ 2026-10 130 139 Using Generative AI to Simulate Item Responses by Skills Insight Score Band Jianshen Chen author Chansoon Lee author Kylie Gorney author Judit Antal author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 chen-etal-2026-using https://aclanthology.org/2026.aimecon-wip.18/ 2026-10 140 144 Exploring AI-driven Methods for Pre-calibrating Difficulty of Mathematics Items with Visual Content Leah Walker author Jinnie Choi author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 walker-choi-2026-exploring https://aclanthology.org/2026.aimecon-wip.19/ 2026-10 145 151 Evaluating Multiple Models for Predicting Item Difficulty in a Principled Assessment Design Alexandra Lane Perez author Christina Schneider author Sangdon Lim author Garron Gianopulos author Kang Xue author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 perez-etal-2026-evaluating https://aclanthology.org/2026.aimecon-wip.20/ 2026-10 152 158 Transformer-Aided Detection of Gaming in Constructed-Response English Language Assessments Melanie Sharif author Scott Hellman author Martha Bellows author Sue Lottridge author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 sharif-etal-2026-transformer https://aclanthology.org/2026.aimecon-wip.21/ 2026-10 159 167 Calibrated, Interpretable Automated Scoring with LLM Likelihoods Thomas Christie author Markus Hauru author Anna Rafferty author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 christie-etal-2026-calibrated https://aclanthology.org/2026.aimecon-wip.22/ 2026-10 168 176 Predicting Item-to-Range Performance Level Descriptor Matches with Structured Language Model Reasoning Kang Xue author M Christina Schneider author Sangdon Lim author Garron Gianopulos author Alexandra Perez author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 xue-etal-2026-predicting https://aclanthology.org/2026.aimecon-wip.23/ 2026-10 177 183 Using LLM Judges’ Paired Comparisons to Estimate Mathematics Item Difficulty Lanrong Li author Mohammad A A Abulela author Matthew Gushta author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 li-etal-2026-using https://aclanthology.org/2026.aimecon-wip.24/ 2026-10 184 192 Math-Specialized or General-Purpose? A Comparison of MathBERT and DeBERTa-v3-large for Automated Scoring of Mathematics-Explanation Items Gregory M Jacobs author Ahmed H Bediwy author Martha Bellows author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 jacobs-etal-2026-math https://aclanthology.org/2026.aimecon-wip.25/ 2026-10 193 199 How Much Does Hyperparameter Tuning Actually Help? An Efficiency Survey for Fine-Tuning Transformers to Score Mathematics-Explanation Items Gregory M Jacobs author Ahmed H Bediwy author Martha Bellows author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 jacobs-etal-2026-much https://aclanthology.org/2026.aimecon-wip.26/ 2026-10 200 206 Responsible use of generative AI when creating reading comprehension questions: Inference matters Zuowei Wang author Michael Flor author Jiyun Zu author Tenaha O’Reilly author Wanjing Anya Ma author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 wang-etal-2026-responsible https://aclanthology.org/2026.aimecon-wip.27/ 2026-10 207 210 Fine-tuning DeBERTa-v3 to Automate Spatial Language Classification Sam Agnoli author Qingzhou Shi author David Uttal author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 agnoli-etal-2026-fine https://aclanthology.org/2026.aimecon-wip.28/ 2026-10 211 215 CDM Q-Matrix Discovery with LLMs: Fusing Domain Knowledge with Empirical Evidence Susu Zhang author V N Vimal Rao author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 zhang-rao-2026-cdm https://aclanthology.org/2026.aimecon-wip.29/ 2026-10 216 230 Composite Scores vs. Preference Rankings: Measuring Architecture Effects in LLM Feedback Harvey Ngoe Kolle author Carrie Demmans Epp author Amna Liaqat author Maria Cutumisu author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 kolle-etal-2026-composite https://aclanthology.org/2026.aimecon-wip.30/ 2026-10 231 234 Identifying Communication Profiles from Physician–Patient Conversations Using Large Language Models Reyhaneh Hosseinpourkhoshkbari author Yash Bipin Jain author Richard Golden author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 hosseinpourkhoshkbari-etal-2026-identifying https://aclanthology.org/2026.aimecon-wip.31/ 2026-10 235 247 LLM-Based Pairwise Judgment for Math Item Parameter Modeling Using Workflows and Agents Suhwa Han author Frank Rijmen author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 han-rijmen-2026-llm https://aclanthology.org/2026.aimecon-wip.32/ 2026-10 248 259 Beyond Volume: How Cognitive Fingerprints Predict Residual Gain in AI Tutoring Aleena K Raj author Nina Deng author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 raj-deng-2026-beyond https://aclanthology.org/2026.aimecon-wip.33/ 2026-10 260 266 Automatic Prompt Engineering for Generative AI–Based Essay Scoring Yue Huang author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 huang-2026-automatic https://aclanthology.org/2026.aimecon-wip.34/ 2026-10 267 274 A Comprehensive Evaluation of GenAI-based Items in a Medical Examination Yanlin Jiang author Marcus Walker author Andrew Dallas author Aquia Richburg author Nikole Gregg author Brittany Corrigan author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 jiang-etal-2026-comprehensive https://aclanthology.org/2026.aimecon-wip.35/ 2026-10 275 281 When One Benchmark Hides Many Truths: Mixture-IRT and LLM Difficulty Prediction Enis Dogan author Burhan Ogut author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 dogan-ogut-2026-one https://aclanthology.org/2026.aimecon-wip.36/ 2026-10 282 288 LLM-As-An-Assessor: Can Open-Weight LLMs Assess Computational Thinking via Student-Designed Embodied Games? William Lee author Sai Gattupalli author Ivon Arroyo author Brendan O’Connor author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 lee-etal-2026-llm-assessor https://aclanthology.org/2026.aimecon-wip.37/ 2026-10 289 297 Funnel Plot Analysis of Examinee Performance in Longitudinal Assessment Aquia Richburg author Marcus Walker author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 richburg-walker-2026-funnel https://aclanthology.org/2026.aimecon-wip.38/ 2026-10 298 305 How Much Training Data Is Enough? Fine-Tuning LLMs for Short-Answer Scoring Joshua A McGrane author David Torres Irribarra author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 mcgrane-torres-irribarra-2026-much https://aclanthology.org/2026.aimecon-wip.39/ 2026-10 306 314 Evaluating Machine Learning, Transformer, and LLM Approaches for Large-Scale Automated Essay Scoring Cyrus Sai-Cheong Chan author Charles Anifowose author Su Zhang author Winnie Wing-Yee Tse author Nizam Radwan author Hyunah Kim author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 chan-etal-2026-evaluating https://aclanthology.org/2026.aimecon-wip.40/ 2026-10 315 321 Construct Validity of Small-Sample Transformer Scoring Models: A Mechanistic Interpretability Approach Michael P Hemenway author Martha Bellows author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 hemenway-bellows-2026-construct https://aclanthology.org/2026.aimecon-wip.41/ 2026-10 322 328 Applying Evidence-Centered Design to Automated Evals of AI-Powered Assessment Systems Kristen DiCerbo author Britte Haugan Cheng author John Whitmer author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 dicerbo-etal-2026-applying https://aclanthology.org/2026.aimecon-wip.42/ 2026-10 329 334 MIST: Misconception Identification and Sycophancy Tracking Lionel Meng author Lingbo Tong author Icy Zhang author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 meng-etal-2026-mist https://aclanthology.org/2026.aimecon-wip.43/ 2026-10 335 343 Building Teacher Capacity to Generate and Evaluate Math Items with Small LLMs Minseok Kim author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 kim-2026-building https://aclanthology.org/2026.aimecon-wip.44/ 2026-10 344 349 Principled Approaches to Building AI Partners for Assessing and Supporting Small-Group Collaboration Peter W Foltz author Chelsea Chandler author Mon-Lin Monica Ko author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 foltz-etal-2026-principled https://aclanthology.org/2026.aimecon-wip.45/ 2026-10 350 357 Measuring Writing Proficiency Through Keystroke Process Data: A Cross-School Generalizability Study Damilola Babalola author Naga Buddarapu author Caleb Scott author Piotr Mitros author Paul Deane author Collin Lynch author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 babalola-etal-2026-measuring https://aclanthology.org/2026.aimecon-wip.46/ 2026-10 358 368 Self-Revising Agents as Item Writers: Benchmarking Against Professional Item Writing Steven Tang author Zhen Li author Richard Patz author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 tang-etal-2026-self https://aclanthology.org/2026.aimecon-wip.47/ 2026-10 369 376 Evaluating Neural Network-Based IRT in Multistage Adaptive Testing with Small Item Banks Seong Eun Hong author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 hong-2026-evaluating https://aclanthology.org/2026.aimecon-wip.48/ 2026-10 377 381 Validating LLM-Rated Item Features for Explanatory Item Response Models Ahmed H Bediwy author Mubarak O Mojoyinola author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 bediwy-mojoyinola-2026-validating https://aclanthology.org/2026.aimecon-wip.49/ 2026-10 382 388 Efficacy of Student–AI Co-Authored Math Word Problems in an Intelligent Tutoring System Kole Norberg author April Murphy author Steve Fancsali author Steve Ritter author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 norberg-etal-2026-efficacy https://aclanthology.org/2026.aimecon-wip.50/ 2026-10 389 396 Assessing Small Language Models as Decimal-Arithmetic Tutors: A Measurement Framework Mai Que Vuong author Shahana Ahmadli author Michelle Zhou author Minseok Kim author Shruti Mehta author Talita de Paula Cypriano de Souza author Seiji Isotani author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 vuong-etal-2026-assessing https://aclanthology.org/2026.aimecon-wip.51/ 2026-10 397 404 LLM as Investigator and Judge in Pairwise Comparisons for Item Parameter Modeling Brian Harrold author Vincent Fakiyesi author Maria D’Brot author Susan Lottridge author Justin Barber author Michael Hemenway author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 harrold-etal-2026-llm https://aclanthology.org/2026.aimecon-wip.52/ 2026-10 405 415 LLM-Based Metadiscourse Analysis of Demographic Variations in ELL Hedge Use Xinyu Xu author Tianyu Xu author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 xu-xu-2026-llm https://aclanthology.org/2026.aimecon-wip.53/ 2026-10 416 422 Beyond the Grid: Auditing Code-Editing Search for Automated Essay Scoring Julius Frost author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 frost-2026-beyond https://aclanthology.org/2026.aimecon-wip.54/ 2026-10 423 440 LLM Difficulty Prediction Across Three L2 Task Types and Two Examination Forms Meng Lyu author Moses Oluoke Omopekunola author Feng Wang author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 lyu-etal-2026-llm https://aclanthology.org/2026.aimecon-wip.55/ 2026-10 441 447 Measuring Science Teachers’ Generative AI Literacy for Classroom Assessment: Performance Assessment Ruiping Huang author Yue Yin author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 huang-yin-2026-measuring https://aclanthology.org/2026.aimecon-wip.56/ 2026-10 448 458 Do Synthetic Students Thrive? Validity and Fairness of Generated Assessment Data Neba Nfonsang author Temple Lovelace author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 nfonsang-lovelace-2026-synthetic https://aclanthology.org/2026.aimecon-wip.57/ 2026-10 459 463 AI-Enabled Quality Assurance for Multiple-Choice Assessment Items Steven James Moore author Nicholas Diana author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 moore-diana-2026-ai https://aclanthology.org/2026.aimecon-wip.58/ 2026-10 464 471 More than Words: Modeling What Teachers Praise and How They Praise It Jiseung Yoo author Paiheng Xu author Jing Liu author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 yoo-etal-2026-words https://aclanthology.org/2026.aimecon-wip.59/ 2026-10 472 482 Does an Automated Source Integration Score Respond to Revision? Extending Evidence of Construct Validity with a Feedback Experiment Andrew Potter author Yu Tian author Kaitlin Van Houghton author Manmeet Singh author Renu Balyan author Maria Goldshtein author Laura K Allen author Danielle S McNamara author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress Joshua Wilson editor Christopher Ormerod editor Magdalen Beiting-Parrish editor National Council on Measurement in Education (NCME) Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States conference publication 979-8-9983004-1-7 potter-etal-2026-automated https://aclanthology.org/2026.aimecon-wip.60/ 2026-10 483 490