EvalLAC 2025
Second Workshop on Automated Evaluation of Learning and Assessment Content

Table of Contents

• Preface
  Summary: There were 23 papers submitted for peer-review to this workshop. Out of these, 9 papers were accepted for this volume, 7 as regular papers and 2 as short papers.

Technical papers

• Leveraging AI Graders for Missing Score Imputation to Achieve Accurate Ability Estimation in Constructed-Response Tests
  Masaki Uto , Yuma Ito
• Domain-Adaptive Automated Essay Scoring with Topic Relevance Learning
  Sungjin Nam
• Automating Pedagogical Evaluation of LLM-based Conversational Agents
  Zaki Pauzi , Michael Dodman , Manolis Mavrikis
• Ordinality in Discrete-level Question Difficulty Estimation: Introducing Balanced DRPS and OrderedLogitNN
  Arthur Thuy , Ekaterina Loginova , Dries Benoit
• Open-Ended Questions Need Personalized Feedback: Analyzing LLM-Enabled Features with Student Data
  Rachel Van Campenhout , Jeffrey S. Dittel , Bill Jerome , Michelle W. Clark , Benny G. Johnson
• Enhancing Neural Automated Essay Scoring Accuracy by Removing Noisy Data Through Data Valuation
  Takumi Shibata , Yuto Tomikawa , Yuki Ito , Masaki Uto
• Fine-tuning for Better Few Shot Prompting: An Empirical Comparison for Short Answer Grading
  Joel Walsh , Siddarth Mamidanna , Benjamin Nye , Mark Core , Daniel Auerbach
• Comparing Human and LLM Evaluations on AI-Generated Critical Thinking Items: Implications for Valid Applications of Automatic Item Generation
  Euigyum Kim , Salah Khalil , Hyo Jeong Shin
• Leveraging the Intuitions of Lay People on Linguistic Complexity for Automatic Sentence Readability Assessment
  Ignatios Charalampidis , Xiaobin Chen