Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers

Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 aime-con-2026-sessions https://aclanthology.org/2026.aimecon-sessions.0/ Multi-Agent LLM Annotation and Scoring for Training Fine-Grained K-12 Writing-Feedback Models Justin O Barber author Michael P Hemenway author Martha Bellows author Susan Lottridge author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 barber-etal-2026-multi https://aclanthology.org/2026.aimecon-sessions.1/ 2026-10 1 8 LLM-Based Rubric Refinement in Multi-Agent Automated Scoring Alexander Kwako author Cristina Everett author Harry Wang author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 kwako-etal-2026-llm https://aclanthology.org/2026.aimecon-sessions.2/ 2026-10 9 22 Beyond Agreement: Operational Monitoring of K–12 Automated Scoring Jing Ma author Edward W Wolfe author Anthony D Fina author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 ma-etal-2026-beyond-agreement https://aclanthology.org/2026.aimecon-sessions.3/ 2026-10 23 30 Detecting Invalid Responses in Automated Essay Scoring with Fine-Tuned Large Language Models YoungKoung Kim author Christopher Ormerod author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 kim-ormerod-2026-detecting https://aclanthology.org/2026.aimecon-sessions.4/ 2026-10 31 38 Beyond Clean Agreement: A Stability-Bounded Evaluation of Compact AES Distillation Yi Gui author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 gui-2026-beyond https://aclanthology.org/2026.aimecon-sessions.5/ 2026-10 39 48 From Efficiency to Sufficiency: A Measurement-Informed Framework for Cost-Aware Automated Essay Scoring Yi Gui author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 gui-2026-efficiency https://aclanthology.org/2026.aimecon-sessions.6/ 2026-10 49 58 Generalizability Theory for Evaluating Fine-Tuned LLMs in Automated Item Generation Zhifei Li author Won-Chan Lee author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 li-lee-2026-generalizability https://aclanthology.org/2026.aimecon-sessions.7/ 2026-10 59 69 Evaluating Score Dependability in ChatGPT-Supported AP Chinese Speaking Tasks Dan Song author Won-Chan Lee author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 song-lee-2026-evaluating https://aclanthology.org/2026.aimecon-sessions.8/ 2026-10 70 75 From Validation to Resilience: Sustaining Measurement Quality in AI-Assisted Enemy Item Identification Ye Ma author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 ma-2026-validation https://aclanthology.org/2026.aimecon-sessions.9/ 2026-10 76 81 Semantic Variability of LLM-Generated Replies Across LLMs: Implications for Designing Conversation-Based Assessment Jiangang Hao author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 hao-2026-semantic https://aclanthology.org/2026.aimecon-sessions.10/ 2026-10 82 88 Resilience Infrastructure for Conversational AI-Based Educational Applications Andrew Emerson author Keelan Evanini author Kevin Frome author Le An Ha author Peter Baldwin author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 emerson-etal-2026-resilience https://aclanthology.org/2026.aimecon-sessions.11/ 2026-10 89 100 Responsible AI in the Duolingo English Test: Case Studies with Automatic Item Creation and Session-Level Quality Monitoring Siyuan Marco Chen author Xiaowan Zhang author Andrew Runge author Jacqueline Church author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 chen-etal-2026-responsible https://aclanthology.org/2026.aimecon-sessions.12/ 2026-10 101 109 Developing and evaluating an AI agent to read and interpret learning maps Dante Cisterna author Jonathan Schuster author Amber Samson author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 cisterna-etal-2026-developing https://aclanthology.org/2026.aimecon-sessions.13/ 2026-10 110 117 Learning Progression-Guided Scientific Model Assessment Using Foundation and Supervised Vision Models Leonora Kaldaras author Yasasvi Nalla author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 kaldaras-nalla-2026-learning https://aclanthology.org/2026.aimecon-sessions.14/ 2026-10 118 123 Developing an LLM Tutor Quality Evaluation Scale Michael Xiao author Zewei Tian author Alex Liu author Lief Esbenshade author Min Sun author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 xiao-etal-2026-developing https://aclanthology.org/2026.aimecon-sessions.15/ 2026-10 124 145 When Language Becomes a Shortcut in Automated Short-Answer Scoring Xiaomeng Xiong author Corinne Huggins-Manley author Jinnie Shin author Christan Grant author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 xiong-etal-2026-language https://aclanthology.org/2026.aimecon-sessions.16/ 2026-10 146 163 Disentangling Severity and Centrality: Rater Effects in LLM-Based Automated Short-Answer Scoring Xiaomeng Xiong author Corinne Huggins-Manley author Jinnie Shin author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 xiong-etal-2026-disentangling https://aclanthology.org/2026.aimecon-sessions.17/ 2026-10 164 179 From Expert Approval to Validity Evidence: Evaluating AI-Generated Assessment Items Chris Meador author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 meador-2026-expert https://aclanthology.org/2026.aimecon-sessions.18/ 2026-10 180 188 Evaluating an AI-Item Generation Tool for NAEP Reading Cara Marie DiMeglio author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 dimeglio-2026-evaluating https://aclanthology.org/2026.aimecon-sessions.19/ 2026-10 189 195 Evaluating an AI-Item Generation Tool for NAEP Mathematics Cheryl Van Ness author Ilona Minchuk author Karen Parker author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 van-ness-etal-2026-evaluating https://aclanthology.org/2026.aimecon-sessions.20/ 2026-10 196 202 Evaluating an AI-Item Generation Tool for NAEP Science Carolina Safar author Mitchell Price author Jeffery Ackley author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 safar-etal-2026-evaluating https://aclanthology.org/2026.aimecon-sessions.21/ 2026-10 203 209 Evidence-Centered Design for AI-Driven Automated Item Generation in Applied Mathematics Edith Aurora Graf author Maria Elena Oliveri author Giulia Oliveri author Emily Proctor author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 graf-etal-2026-evidence https://aclanthology.org/2026.aimecon-sessions.22/ 2026-10 210 218 Human–AI Collaboration in Educational Measurement: Transforming Assessment Data into Educational Action Laura C Egan author Judy H Tang author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 egan-tang-2026-human https://aclanthology.org/2026.aimecon-sessions.23/ 2026-10 219 224 Scaling Human-AI Collaboration: Translating Multi-Source Assessment Data into Formative Learner Profiles Hongwen Guo author Matthew S Johnson author Luis Saldivia author Michelle Worthington author Jeremy Lee author Kadriye Ercikan author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 guo-etal-2026-scaling https://aclanthology.org/2026.aimecon-sessions.24/ 2026-10 225 235 Human–Machine Learning for Large-Scale Qualitative Coding in Educational Measurement Judy H Tang author Tom Krenzke author Jin Hui Xu author Karen Lo author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 tang-etal-2026-human https://aclanthology.org/2026.aimecon-sessions.25/ 2026-10 236 240 Rubric-Aligned Generative-AI Features as Supplementary Predictors in Feature-Based Automated Essay Scoring Yue Huang author Duanli Yan author Corey Palermo author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 huang-etal-2026-rubric https://aclanthology.org/2026.aimecon-sessions.26/ 2026-10 241 250 Latent Factors of Discourse Type and Effectiveness in PERSUADE 2.0 for AES Yi Gui author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 gui-2026-latent https://aclanthology.org/2026.aimecon-sessions.27/ 2026-10 251 259 Rethinking Validity in Educational Assessment when AI Co-Produces Performance Xiaoran Li author Tanesia Beverly author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 li-beverly-2026-rethinking https://aclanthology.org/2026.aimecon-sessions.28/ 2026-10 260 266 Programmatic Tiered Prompting for LLM Generation of ELA & Math Items David Whitecomb author Marjorie Wine author Alexander Hoffman author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 whitecomb-etal-2026-programmatic https://aclanthology.org/2026.aimecon-sessions.29/ 2026-10 267 273 The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization Okan Bulut author Bin Tan author Elisabetta Mazzullo author Cole Walsh author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 bulut-etal-2026-scoring https://aclanthology.org/2026.aimecon-sessions.30/ 2026-10 274 283 Can LLMs detect item flaws in the questions they have generated? Guher Gorgun author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 gorgun-2026-llms https://aclanthology.org/2026.aimecon-sessions.31/ 2026-10 284 290 Automated Evaluation of Mathematical Equivalence Between Personalized and Standard Word Problems Burcu Arslan author Ikkyu Choi author Jesse R Sparks author Reginald M Gooch author Candace Walkington author Matthew L Bernacki author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 arslan-etal-2026-automated https://aclanthology.org/2026.aimecon-sessions.32/ 2026-10 291 305 Next Skill Evaluation & Targeting via Map-Based Analytics Jeff Hoover author Amy Clark author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 hoover-clark-2026-next https://aclanthology.org/2026.aimecon-sessions.33/ 2026-10 306 311 Score Report Conversational Agent to Guide Educators in Interpreting Assessment Results Brian D Gane author Dante I Cisterna author Amy K Clark author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 gane-etal-2026-score https://aclanthology.org/2026.aimecon-sessions.34/ 2026-10 312 319 Automated Generation and Scoring of Maze Reading Comprehension Assessments Hatice Kubra Karakis author Walter Leite author Logan Scott author Xinyi Tai author Akihito Kamata author 2026-10 text Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers 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 979-8-9983004-2-4 karakis-etal-2026-automated https://aclanthology.org/2026.aimecon-sessions.35/ 2026-10 320 328