AIED 2025 workshop | Palermo (Italy), Hybrid | July 26 (Full day)
Archival
Paper 1: Leveraging AI Graders for Missing Score Imputation to Achieve Accurate Ability Estimation in Constructed-Response Tests. Masaki Uto and Yuma Ito. | PDF | Poster |
Paper 3: Domain-Adaptive Automated Essay Scoring with Topic Relevance Learning. Sungjin Nam. | PDF | Poster |
Paper 4: Automating pedagogical evaluation of LLM-based conversational agents. Zaki Pauzi, Michael Dodman and Manolis Mavrikis. | PDF | Poster |
Paper 6: Ordinality in Discrete-level Question Difficulty Estimation: Introducing Balanced DRPS and OrderedLogitNN. Arthur Thuy, Ekaterina Loginova and Dries Benoit. | PDF | Poster |
Paper 7: Open-Ended Questions Need Personalized Feedback: Analyzing LLM-Enabled Features with Student Data. Rachel Van Campenhout, Jeff Dittel, Bill Jerome, Michelle Clark and Benny Johnson. | PDF | Poster |
Paper 9: Enhancing Neural Automated Essay Scoring Accuracy by Removing Noisy Data Through Data Valuation. Takumi Shibata, Yuto Tomikawa, Yuki Ito and Masaki Uto. | PDF | Poster |
Paper 19: Fine-tuning for Better Few Shot Prompting: An Empirical Comparison for Short Answer Grading. Joel Walsh, Siddarth Mamidanna, Benjamin Nye, Mark G. Core and Daniel Auerbach. | PDF | Poster |
Paper 22: Comparing Human and LLM Evaluations on AI-Generated Critical Thinking Items: Implications for Valid Applications of Automatic Item Generation. Euigyum Kim, Salah Khalil and Hyo Jeong Shin. | PDF | Poster |
Paper 23: Leveraging the Intuitions of Lay People on Linguistic Complexity for Automatic Sentence Readability Assessment. Ignatios Charalampidis and Xiaobin Chen. | PDF | Poster |
Non-Archival
Paper 8: Assessing learning materials: hybrid vs Large Language Model-based generation of grammar exercises. Lucas Poirot and Yannick Parmentier. | PDF | Poster |
Paper 15: More Brains: When Multi-Agent Systems Outperform Single-Agent Evaluation of Collaborative Math Tasks. Yu Wang, Madhumitha Gopalakrishnan, Ella Anghel and Yoav Bergner. | PDF | Poster |
Paper 21: Comparing Traditional and LLM-based Approaches for Automated Scoring of Dutch Writing Products. Joni Kruijsbergen and Orphée De Clercq. | PDF | Poster |