20th Workshop on Innovative Use of NLP for Building Educational Applications: Schedule
- Time Zone
- Europe/Vienna: CEST (Central European Summer Time), UTC+2
- Location
- In-person: Room 1.85–86
Virtual: Underline.io [Day 1] [Day 2] - Add to Calendar
- Stay on schedule—download the full workshop program here: Download ICS
- Schedule Changes
- Please check for any last-minute changes here.
Thursday, July 31, 2025
Below is the schedule for the first workshop day. The tutorial slides are available online and can be accessed by clicking the tutorial link. Each paper in the oral and poster sessions is linked to its page on Underline; you can find the pre-recorded video there. Most oral presentations will be in person but can be followed through livestream. Poster presentations may be in person (in the posters area) or online (on Gather Town). The ID next to a poster represents the poster board ID. To join the workshop online or by livestream, please connect to the Workshop Day 1 on Underline.io.
| Time | Description |
|---|---|
| 09:00 - 10:30 | Tutorial Session A LLMs for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward Chair: Victoria Yaneva |
| 10:30 - 11:00 | Coffee Break |
| 11:00 - 12:30 | Tutorial Session B LLMs for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward Chair: Bashar Alhafni |
| 12:30 - 14:00 | Lunch Break Birds of a Feather: Writing Assistants Organizer: Bashar Alhafni |
| 14:00 - 15:30 | Oral Session A Chair: Anaïs Tack |
| 14:00 - 14:15 | A Bayesian Approach to Inferring Prerequisite Structures and Topic Difficulty in Language Learning (Anh-Duc Vu, Jue Hou, Anisia Katinskaia, Ching-Fan Sheu, Roman Yangarber)   |
| 14:15 - 14:30 | Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection (Chatrine Qwaider, Bashar Alhafni, Kirill Chirkunov, Nizar Habash, Ted Briscoe) |
| 14:30 - 14:45 | Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring (Mina Almasi, Ross Kristensen-McLachlan) |
| 14:45 - 15:00 | You Shall Know a Word’s Difficulty by the Family It Keeps: Word Family Features in Personalised Word Difficulty Classifiers for L2 Spanish (Jasper Degraeuwe) |
| 15:00 - 15:15 | Assessing Critical Thinking Components in Romanian Secondary School Textbooks: A Data Mining Approach to the ROTEX Corpus (Madalina Chitez, Liviu Dinu, Marius Micluta-Campeanu, Ana-Maria Bucur, Roxana Rogobete) |
| 15:15 - 15:30 | Unsupervised Automatic Short Answer Grading and Essay Scoring: A Weakly Supervised Explainable Approach (Felipe Urrutia, Cristian Buc, Roberto Araya, Valentin Barriere) |
| 15:30 - 16:00 | Coffee Break |
| 16:00 - 17:30 | Poster Session A Hall X5 (in person, boards #1-11, #36-46) Gather Town (online) |
| Hall #1 |
A Survey on Automated Distractor Evaluation in Multiple-Choice Tasks (Luca Benedetto, Shiva Taslimipoor, Paula Buttery)   |
| Hall #2 |
Increasing the Generalizability of Similarity-Based Essay Scoring Through Cross-Prompt Training (Marie Bexte, Yuning Ding, Andrea Horbach) |
| Hall #3 |
Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings (Kordula De Kuthy, Leander Girrbach, Detmar Meurers) |
| Hall #4 |
Automated Scoring of a German Written Elicited Imitation Test (Mihail Chifligarov, Jammila Laâguidi, Max Schellenberg, Alexander Dill, Anna Timukova, Anastasia Drackert, Ronja Laarmann-Quante) |
| Hall #5 |
Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison (Aymeric de Chillaz, Anna Sotnikova, Patrick Jermann, Antoine Bosselut) |
| Hall #6 |
Don’t Score too Early! Evaluating Argument Mining Models on Incomplete Essays (Nils-Jonathan Schaller, Yuning Ding, Thorben Jansen, Andrea Horbach) |
| Hall #7 |
LangEye: Toward ‘Anytime’ Learner-Driven Vocabulary Learning From Real-World Objects (Mariana Shimabukuro, Deval Panchal, Christopher Collins) |
| Hall #8 |
Explaining Holistic Essay Scores in Comparative Judgment Assessments by Predicting Scores on Rubrics (Michiel De Vrindt, Renske Bouwer, Wim Van Den Noortgate, Marije Lesterhuis, Anaïs Tack) |
| Hall #9 |
Name of Thrones: How Do LLMs Rank Student Names in Status Hierarchies Based on Race and Gender? (Annabella Sakunkoo, Jonathan Sakunkoo) |
| Hall #10 |
Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems (Sahar Yarmohammadtoosky, Yiyun Zhou, Victoria Yaneva, Peter Baldwin, Saed Rezayi, Brian Clauser, Polina Harik) |
| Hall #11 |
Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian (Martin Vainikko, Taavi Kamarik, Karina Kert, Krista Liin, Silvia Maine, Kais Allkivi, Annekatrin Kaivapalu, Mark Fishel) |
| Hall #36 |
Can LLMs Reliably Simulate Real Students’ Abilities in Mathematics and Reading Comprehension? (KV Aditya Srivatsa, Kaushal Maurya, Ekaterina Kochmar) |
| Hall #37 |
Transformer Architectures for Vocabulary Test Item Difficulty Prediction (Lucy Skidmore, Mariano Felice, Karen Dunn) |
| Hall #38 |
Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features (Hakyung Sung, Karla Csuros, Min-Chang Sung) |
| Hall #39 |
Comparing Behavioral Patterns of LLM and Human Tutors: A Population-level Analysis with the CIMA Dataset (Aayush Kucheria, Nitin Sawhney, Arto Hellas) |
| Hall #40 |
MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks (Marius Dumitran, Mihnea Buca, Theodor Moroianu) |
| Hall #41 |
Advancing Question Generation with Joint Narrative and Difficulty Control (Bernardo Leite, Henrique Lopes Cardoso) |
| Hall #42 |
Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation (Kseniia Petukhova, Ekaterina Kochmar) |
| Hall #43-#46 |
Available Poster Slots ACL 2025 Papers on Educational Applications |
| Gather #150 |
EduCSW: Building a Mandarin-English Code-Switched Generation Pipeline for Computer Science Learning (Ruishi Chen, Yiling Zhao)  |
| Investigating Methods for Mapping Learning Objectives to Bloom’s Revised Taxonomy in Course Descriptions for Higher Education (Zahra Kolagar, Frank Zalkow, Alessandra Zarcone) |
|
| Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation (Nhat Tran, Diane Litman, Benjamin Pierce, Richard Correnti, Lindsay Clare Matsumura) |
|
| Using NLI to Identify Potential Collocation Transfer in L2 English (Haiyin Yang, Zoey Liu, Stefanie Wulff) |
|
| UPSC2M: Benchmarking Adaptive Learning from Two Million MCQ Attempts (Kevin Shi, Karttikeya Mangalam) |
|
| Multilingual Grammatical Error Annotation: Combining Language-Agnostic Framework with Language-Specific Flexibility (Mengyang Qiu, Tran Minh Nguyen, Zihao Huang, Zelong Li, Yang Gu, Qingyu Gao, SILIANG LIU, Jungyeul Park) |
|
| Gather #70 |
Automatic Generation of Inference Making Questions for Reading Comprehension Assessments (Wanjing (Anya) Ma, Michael Flor, Zuowei Wang) |
| Gather #107 |
Lessons Learned in Assessing Student Reflections with LLMs (Mohamed Elaraby, Diane Litman) |
| Gather #69 |
Automated L2 Proficiency Scoring: Weak Supervision, Large Language Models, and Statistical Guarantees (Aitor Arronte Alvarez, Naiyi Xie Fincham) |
| Advances in Auto-Grading with Large Language Models: A Cross-Disciplinary Survey (Tania Amanda Nkoyo Frederick Eneye, Chukwuebuka Fortunate Ijezue, Ahmad Imam Amjad, Maaz Amjad, Sabur Butt, Gerardo Castañeda-Garza) |
|
| Gather #123 |
Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues (Fareya Ikram, Alexander Scarlatos, Andrew Lan) |
| Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic (Zhenjiang Mao, Artem Bisliouk, Rohith Nama, Ivan Ruchkin) |
|
| 17:30 - 18:00 | Meetup and Group Picture Conference Center Entrance |
| 18:00 - 21:00 | Workshop Dinner Due to the impressive turnout and interest this year, dinner will be organized on a first come, first served basis, with everyone meeting at the entrance to head to the restaurant as a group. Please be aware that dinner reimbursement is available only for student participants. If the group size exceeds the restaurant’s capacity, alternative plans include riding the metro to the lively Prater—an open theme park with local food and famous for its iconic (James Bond) ferris wheel—or enjoying a bite at the nearby food market. |
Friday, August 1, 2025
Below is the schedule for the second workshop day. Each paper in the oral and poster sessions is linked to its page on Underline; you can find the pre-recorded video there. To join the workshop by livestream, please connect to the Workshop Day 2 on Underline.io.
