BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME:BEA 2026
PRODID:-//Anaïs Tack//Emacs with Org mode//EN
X-WR-TIMEZONE:CEST
X-WR-CALDESC:The 21st Workshop on Innovative Use of NLP for Building Educat
 ional Applications
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-a697baf6-1614-4f04-9727-bfee9c557c25
DTSTART;TZID=America/Los_Angeles:20260703T060000
DTEND;TZID=America/Los_Angeles:20260703T073000
SUMMARY:BEA 2026: Early Poster Session
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:\n- Using k-Shot Prompting with Large k for the Automated Scori
 ng of a German Written Elicited Imitation Test (Malte Sternik\, Ronja Laar
 mann-Quante\, Anastasia Drackert)\n- From Questions to Assessment Tuples: 
 A Multi-Agent Framework with Bloom-Specialized Agents and Automated Verifi
 cation (Gee-Lyle Wong\, Runcong Zhao\, Yulan He\, Jiazheng Li)\n- Fine-Gra
 ined Content Zone Prediction in German Argumentative Essays Using LLMs (Xi
 aoyu Bai\, Manfred Stede)\n- Sharing is Caring: Advantages of Sharing a La
 nguage Background with Learners as an Annotator of Learner Data in UD (Car
 oline Grand-Clement\, Arianna Masciolini)\n- The Effects of Structured LLM
 -Generated Feedback on Programming Assignment Performance (Tsvetomila Miha
 ylova\, Evanfiya Logacheva\, Arto Hellas\, Jing Fan\, Francisco Castro\, B
 ita Akram\, Narges Norouzi\, Peter Brusilovsky\, Juho Leinonen)\n- HFT at 
 BEA 2026 Shared Task 2: Blunt-Edge Models for Hybrid Grading (Ulrike Pado)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-c212a2e2-9fba-4a2a-8ad6-af793cbe3cad
DTSTART;TZID=America/Los_Angeles:20260703T073000
DTEND;TZID=America/Los_Angeles:20260703T084500
SUMMARY:BEA 2026: Early Oral Session
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-08a49919-055b-4481-8d8f-37a0c847193f
DTSTART;TZID=America/Los_Angeles:20260703T073000
DTEND;TZID=America/Los_Angeles:20260703T074500
SUMMARY:Domain-Adaptive Pre-training for Automated Short Answer Grading in 
 Conceptual Physics: Reliability\, Question-Level Analysis\, and Error Redu
 ction
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Shirin Lade\, Alistair Willis\, Jonathan Nylk\, Oli How
 son
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-bd706f70-3fd7-4b14-b462-169c0fbe457a
DTSTART;TZID=America/Los_Angeles:20260703T074500
DTEND;TZID=America/Los_Angeles:20260703T080000
SUMMARY:Using Interaction Log Data to Evaluate and Improve Feedback Accurac
 y in an Intelligent Language Tutoring System
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Mariia Soliar\, Leona Colling\, Stephen Bodnar\, Detmar
  Meurers
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-8fe400ca-8245-45c9-972b-0986af5b2df3
DTSTART;TZID=America/Los_Angeles:20260703T080000
DTEND;TZID=America/Los_Angeles:20260703T081500
SUMMARY:Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediati
 on
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Kseniia Petukhova\, Tien Dat Nguyen\, Ekaterina Kochmar
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-8203db09-c6e1-4408-8781-3456e051ec8c
DTSTART;TZID=America/Los_Angeles:20260703T081500
DTEND;TZID=America/Los_Angeles:20260703T083000
SUMMARY:What Aggregate Scores Hide: Per-Rule Evaluation of Russian Grammati
 cal Error Correction
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Anna Smirnova\, Artyom Kopan\, Vladislav Makeev\, Georg
 e Chernishev
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-23d28a6d-55d2-4fc6-8a0d-7916c3e7e8a7
DTSTART;TZID=America/Los_Angeles:20260703T083000
DTEND;TZID=America/Los_Angeles:20260703T084500
SUMMARY:IWM-DKM at BEA 2026 Shared Task 2: Supplementing Supervised Fine-Tu
 ning for Rubric-Based Short Answer Scoring
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Kate Belcher\, Marius De Kuthy Meurers\, Kordula De Kut
 hy\, Detmar Meurers
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-b647037d-2c45-41cc-ab33-9cbb7f174c79
DTSTART;TZID=America/Los_Angeles:20260703T090000
DTEND;TZID=America/Los_Angeles:20260703T103000
SUMMARY:BEA 2026: Tutorial Session A
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Theory of Mind and Application in Educational Context (Effat Fa
 rhana\, Maha Zainab\, Qiaosi Wang\, Niloofar Mireshghallah\, Ramira van de
 r Meulen\, Max van Duijn)\n09:00 - 09:10 Introduction and Background (Effa
 t Farhana)\n09:10 - 09:20 Online Tutoring Systems and Cognitive Modeling (
 Effat Farhana)\n09:20 - 09:35 LLM Adaptation in AI Tutoring (Maha Zainab)\
 n09:35 - 09:50 ToM Integration and Research Gaps (Effat Farhana)\n09:50 - 
 10:00 Synthesis\, Reflection\, and Key Themes of the Tutorial (Effat Farha
 na)\n10:00 - 10:30 ToM and User Privacy (Niloofar Mireshghallah)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-7f160bdb-5da9-4254-9553-32f8b572446b
DTSTART;TZID=America/Los_Angeles:20260703T103000
DTEND;TZID=America/Los_Angeles:20260703T110000
SUMMARY:BEA 2026: Coffee Break
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-6347ebdc-ff07-4022-a419-c5284bf6cea1
DTSTART;TZID=America/Los_Angeles:20260703T110000
DTEND;TZID=America/Los_Angeles:20260703T123000
SUMMARY:BEA 2026: Tutorial Session B
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Theory of Mind and Application in Educational Context (Effat Fa
 rhana\, Maha Zainab\, Qiaosi Wang\, Niloofar Mireshghallah\, Ramira van de
 r Meulen\, Max van Duijn)\n11:00 - 11:25 Addressing Misconceptions (Ramira
  van der Meulen)\n11:25 - 11:50 Mutual ToM in AI Tutoring (Qiaosi Wang - E
 ffat will play recorded talk of Qiaosi as she has time conflict)\n11:50 - 
 12:30 Q&A and Machine ToM in Source Code Comprehension Demo (Maha Zainab)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-a5151e72-32ab-470e-8ce4-d2a6eb999e73
DTSTART;TZID=America/Los_Angeles:20260703T123000
DTEND;TZID=America/Los_Angeles:20260703T140000
SUMMARY:BEA 2026: Lunch Break / Birds of a Feather
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-c4de244b-b7c7-4a30-b405-2175c237f287
DTSTART;TZID=America/Los_Angeles:20260703T140000
DTEND;TZID=America/Los_Angeles:20260703T154500
SUMMARY:BEA 2026: Oral Session A
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-8142f8c1-9cef-4f63-8f3d-f019c1a13b18
DTSTART;TZID=America/Los_Angeles:20260703T140000
DTEND;TZID=America/Los_Angeles:20260703T141500
SUMMARY:Instruction-Following LLMs for Grammatical Error Correction: Analyz
 ing Neutral-Anchored Instructional Sensitivity Across Editing Modes
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Tolgahan Türker\, Gülşen Eryiğit
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-7fb5c5c1-e711-46ff-b942-8e38b8a0f7f6
DTSTART;TZID=America/Los_Angeles:20260703T141500
DTEND;TZID=America/Los_Angeles:20260703T143000
SUMMARY:Estimating LLM Grading Ability and Response Difficulty in Automatic
  Short Answer Grading via Item Response Theory
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Longwei Cong\, Sonja Hahn\, Sebastian Gombert\, Leon Ca
 mus\, Hendrik Drachsler\, Ulf Kroehne
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-d019e79d-8831-499b-9fde-1e3ebea00024
DTSTART;TZID=America/Los_Angeles:20260703T143000
DTEND;TZID=America/Los_Angeles:20260703T144500
SUMMARY:LLM-Powered but Rule-Grounded: Pedagogically Relevant Grammatical E
 rror Characterization for Learner Model Construction
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Soroosh Akef\, Amália Mendes\, P Rebuschat\, Detmar Meu
 rers
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-d15d7f04-6818-40ba-a5f4-c06ef74402a8
DTSTART;TZID=America/Los_Angeles:20260703T144500
DTEND;TZID=America/Los_Angeles:20260703T150000
SUMMARY:KEYSCORE — Keystroke-enhanced Automated Essay Scoring
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:Talk by Nils-Jonathan Schaller\, Daniel Mora Melanchthon\, Thor
 ben Jansen\, Olaf Köller\, Andrea Horbach
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-ea32036b-a5d1-4110-9ca3-08ab3b696bc6
DTSTART;TZID=America/Los_Angeles:20260703T151500
DTEND;TZID=America/Los_Angeles:20260703T173000
SUMMARY:BEA 2026: Poster Session A
LOCATION:Zoom\nhttps://underline.io/events/530/sessions?eventSessionId=2299
 3
DESCRIPTION:\n- Inferring Student Engagement via Real-Time Thermal–Visual V
 oice Activity Detection (Bradley Goodman)\n- Letting Tutor Personas Speak 
 Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimi
 zation (Jaewook Lee\, Alexander Scarlatos\, Simon Woodhead\, Andrew Lan)\n
 - A Bigger Catch: Fine-Grained Curriculum Standards Alignment on the MathF
 ish Benchmark (Xinman Liu\, Mayank Sharma\, Xinyu Shi)\n- Through the Sent
 ence Lens: Explainable Essay Scoring through Fine-Grained Predictions (Dan
 iel Mora Melanchthon\, Stefan Keller\, Andrea Horbach)\n- Kelvi: A Morphol
 ogical Parser to Support Tamil Literacy (Shankhalika Srikanth\, Sabrina Yu
 \, Sophia Chan\, Madeline Solis de Ovando)\n- Multi-step Large Language Mo
 del for Fine-Grained Feedback in Stepwise Linear Equation Solutions (Imran
  Chamieh\, Torsten Zesch\, Klaus Giebermann)\n- Comparative Evaluation of 
 AI-Generated vs. Expert-written Answer Explanations for a Medical Educatio
 n Self-Assessment (Yiyun Zhou\, Francis O'Donnell\, Victoria Yaneva)\n- PE
 RSA: Reinforcement Learning for Professor-Style Personalized Feedback with
  LLMs (Ravi Kumar\, Utkarsh Grover\, Xiaomin Lin\, Agoritsa Polyzou)\n- Po
 licy-Sensitive Fairness Evaluation in Automated Scoring of Clinical Commun
 ication (Saed Rezayi\, Le An Ha\, Victoria Yaneva\, Polina Harik\, Janet M
 ee\, Jason Snyder)\n- Assessment of L2 speech global dimensions using larg
 e audio language models (Elsayed Issa\, Mahmoud Ali)\n- Children's English
  Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with 
 Controllable Difficulty and Safety (Qian Shen\, Fanghua Cao\, Min Yao\, Sh
 lok Gilda\, Bonnie Dorr\, Walter Leite)\n- Transformer-based readability c
 lassifiers are worse than you think: Evidence from cross-domain Arabic rea
 dability assessment (SARH ALZU'BI\, Robert Reynolds)\n- Predicting Item Di
 fficulty and Generating Reading Comprehension Items via an Annotated Repos
 itory (Radhika Kapoor\, Mayank Sharma\, Sang Truong\, Nick Haber\, Ben Dom
 ingue\, Maria Ruiz-Primo)\n- Generative-Evaluative Agreement: A Necessary 
 Validity Criterion for LLM-Enabled Adaptive Assessment (Grandee Lee\, Yue 
 Wang\, Che Yee Lye\, Luke Peh)\n- Teaching Through Analogies: A Modular Pi
 peline for Educational Analogy Generation (Mariam Barakat\, Ekaterina Koch
 mar)\n- From Dialogue to Learner Modeling: Identifying Candidate Signals o
 f Productive Use in LLM-Based Grammar Practice (Luisa Ribeiro-Flucht\, Lan
 hua Huang\, Xiaobin Chen)\n- SAAKTH at BEA 2026 Shared Task 1: L1-Aware En
 glish Vocabulary Difficulty Prediction with Hybrid Transformer and Psychol
 inguistic Features (Karthik Mattu\, Adit Dhall\, Arshad Naguru\, Shubh Seh
 gal\, Thejas Gowda\, Hakyung Sung)\n- Jinnie's Lab at BEA 2026 Shared Task
  1: Precalibration of Vocabulary Item Difficulty with Multilingual Transfo
 rmers and Multi-Task Learning (Zhe Li\, Pauline Aguinalde\, Jinnie Shin)\n
 - TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction
  with Context-Aligned Contrastive Learning and Ridge Ensembling (wicaksono
  M.\, Joanito Lopo\, Tsamarah Nugraha\, Ahmad Adi\, Muhamad Nurfajri)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-5614d805-3b8a-4f6e-8179-1837cebb5744
DTSTART;TZID=America/Los_Angeles:20260704T090000
DTEND;TZID=America/Los_Angeles:20260704T103000
SUMMARY:BEA 2026: Oral Session B
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-da9bd75a-cfca-4593-9a88-4cc50ba0c3b7
DTSTART;TZID=America/Los_Angeles:20260704T090000
DTEND;TZID=America/Los_Angeles:20260704T091500
SUMMARY:The Aftermath of DrawEduMath: Vision Language Models Underperform w
 ith Struggling Students and Misdiagnose Errors
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Li Lucy\, Albert Zhang\, Nathan Anderson\, Ryan Knight\
 , Kyle Lo
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-552c1f0f-d398-4ea0-bce3-a2a3022387af
DTSTART;TZID=America/Los_Angeles:20260704T091500
DTEND;TZID=America/Los_Angeles:20260704T093000
SUMMARY:Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student D
 ialogues
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Shuyan Huang\, Alexander Scarlatos\, Jaewook Lee\, Andr
 ew Lan
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-78a64d12-98fc-4855-9ddf-aa061a895a53
DTSTART;TZID=America/Los_Angeles:20260704T093000
DTEND;TZID=America/Los_Angeles:20260704T094500
SUMMARY:Measuring Optimal Challenge: Trajectory-Based Difficulty Alignment 
 in Open-Ended Language Tutoring
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Ziqi Shu\, Shuman Wang\, Michael Hardy
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-78a77947-bf9e-4d0e-852b-ab9e2a4f7e75
DTSTART;TZID=America/Los_Angeles:20260704T094500
DTEND;TZID=America/Los_Angeles:20260704T100000
SUMMARY:Findings of the BEA 2026 Shared Task on Vocabulary Difficulty Predi
 ction for English Learners
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Mariano Felice\, Lucy Skidmore
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-ed891202-ab14-419a-9f1e-a8f93e4ddb2c
DTSTART;TZID=America/Los_Angeles:20260704T100000
DTEND;TZID=America/Los_Angeles:20260704T101500
SUMMARY:Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult?
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Adam Nohejl\, Xuanxin Wu\, Yusuke Ide\, Maria Riera Mac
 hin\, Yi-Ning Chang
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-6e6e8859-b262-4983-bb63-0da0cca546a5
DTSTART;TZID=America/Los_Angeles:20260704T101500
DTEND;TZID=America/Los_Angeles:20260704T103000
SUMMARY:Report on the BEA 2026 Shared Task on Rubric-based Short Answer Sco
 ring for German
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Sebastian Gombert\, Zhifan Sun\, Fabian Zehner\, Jannik
  Lossjew\, Tobias Wyrwich\, Berrit Czinczel\, David Bednorz\, Sascha Bernh
 olt\, Knut Neumann\, Ute Harms\, Aiso Heinze\, Hendrik Drachsler
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-b54416b3-4426-42a3-81d1-b4864a2d37fb
DTSTART;TZID=America/Los_Angeles:20260704T103000
DTEND;TZID=America/Los_Angeles:20260704T110000
SUMMARY:BEA 2026: Coffee Break
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-4a84d604-4050-4517-8e35-2cfabc899766
DTSTART;TZID=America/Los_Angeles:20260704T110000
DTEND;TZID=America/Los_Angeles:20260704T123000
SUMMARY:BEA 2026: Oral Session C
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-0f521d2d-2554-4dde-80ed-fb87fc35238d
DTSTART;TZID=America/Los_Angeles:20260704T110000
DTEND;TZID=America/Los_Angeles:20260704T111500
SUMMARY:EduMUSE: A Multimodal Educational Dataset with Automatically Extrac
 ted Instructional Context
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Andreea Dutulescu\, Stefan Ruseti\, Mihai Dascalu\, Dan
 ielle McNamara
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-871fe29f-6243-478e-8348-1cb1a0d7be76
DTSTART;TZID=America/Los_Angeles:20260704T111500
DTEND;TZID=America/Los_Angeles:20260704T113000
SUMMARY:Confirming Correct\, Missing the Rest: LLM Tutoring Agents Struggle
  Where Feedback Matters Most
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Tahreem Yasir\, Wenbo Li\, Sam Gilson\, Sutapa Tithi\, 
 Xiaoyi Tian\, Tiffany Barnes
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-bdfd3b41-03ef-432d-9202-d934e32526b9
DTSTART;TZID=America/Los_Angeles:20260704T113000
DTEND;TZID=America/Los_Angeles:20260704T114500
SUMMARY:Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning 
 via Knowledge-Grounded LLM
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Younghun Lee\, Amir Bralin\, Nobel Sanjay Rebello\, Dan
  Goldwasser
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-bafa0a50-9452-430e-a3f5-c6a67afee374
DTSTART;TZID=America/Los_Angeles:20260704T114500
DTEND;TZID=America/Los_Angeles:20260704T120000
SUMMARY:Evaluating LLM Workflows for Generating Clinical Communication Asse
 ssment Items: A Comparative Study with Subject-Matter Experts
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Christopher Runyon\, Peter Baldwin\, Ian Micir\, Kevin 
 Frome\, Stephanie Mann\, Saed Rezayi\, Keelan Evanini\, Victoria Yaneva
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-70a0f590-baf8-4873-93c4-c6ac40bbda41
DTSTART;TZID=America/Los_Angeles:20260704T120000
DTEND;TZID=America/Los_Angeles:20260704T121500
SUMMARY:Zero Shot Phonics: Evaluating Constraint-Adherent Phonics Story Gen
 eration in Large Language Models
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Maria Monica Manlises\, Ethel Ong
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-f2956399-7733-409b-b662-f74b2d2b756e
DTSTART;TZID=America/Los_Angeles:20260704T121500
DTEND;TZID=America/Los_Angeles:20260704T123000
SUMMARY:Evaluating Adaptive Personalization of Educational Readings with Si
 mulated Learners
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Ryan Woo\, Anmol Rao\, Aryan Keluskar\, Yinong Chen
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-6b073ce2-16d9-4acc-a30f-08b5fe274e07
DTSTART;TZID=America/Los_Angeles:20260704T123000
DTEND;TZID=America/Los_Angeles:20260704T140000
SUMMARY:BEA 2026: Lunch Break / Birds of a Feather
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-c9e43c84-11dd-4039-acb2-3de561512242
DTSTART;TZID=America/Los_Angeles:20260704T140000
DTEND;TZID=America/Los_Angeles:20260704T153000
SUMMARY:BEA 2026: Poster Session B
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:\n- Investigating Context-aware CTC for Pronunciation Assessmen
 t: Mitigating Peaky Behavior and Context Independency Assumption (Jiun-Tin
 g Li\, Tien-Hong Lo\, Bi-Cheng Yan\, Shih-Hsuan Chiu\, Fu-An Chao\, Berlin
  Chen)\n- A Survey of Automated Presentation Coaching: Systems\, Methods\,
  and Open Challenges (Wen Liang\, Li Siyan\, Zackary Rackauckas\, Julia Hi
 rschberg)\n- Criterial Features in German: Towards Interpretable NLP in Re
 adability Assessment (Denise Loefflad\, Sofia Kathmann\, Heiko Holz\, Detm
 ar Meurers)\n- RABIT: Rationale-Based Distillation Towards Interpretable A
 utomatic Speaking Assessment via a Small Language Model (Bi-Cheng Yan\, Ho
 ng-Yun Lin\, Fu-An Chao\, Jiun-Ting Li\, Berlin Chen)\n- Challenges in Mac
 hine Translation of Interactive Multimodal Exercises (Lucie Polakova\, Mir
 oslav Hrabal\, Věra Kloudová\, Michal Novák\, Mariia Anisimova\, Martin Po
 pel)\n- Towards Self-Referential Analytic Assessment: A Profile-Based Appr
 oach to L2 Writing Evaluation with LLMs (Stefano Banno\, Kate Knill\, Mark
  Gales)\n- Assessing the Quality and Consistency of Automated Knowledge Co
 mponent Generation using Instructor-generated Questions and LLMs (Jordan E
 siason\, Priyanka Khare\, Wookhee Min\, Seung Lee\, Gamze Ozogul\, Xiaoyin
 g Zheng\, Yeil Jeong)\n- Intent vs. Surface: Recovering Acoustic Realizati
 on from Modern ASR for Pronunciation Training (Seongjin Park)\n- Opportuni
 ties and Challenges of LLMs in Education: An NLP Perspective (Sowmya Vajja
 la\, Bashar Alhafni\, Stefano Banno\, Kaushal Maurya\, Ekaterina Kochmar)\
 n- Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Ra
 nge Degradation and the Impact of Task-Specific Adaptation (Abigail Gurin 
 Schleifer\, Moriah Ariely\, Beata Beigman Klebanov\, Asaf Salman\, Giora A
 lexandron)\n- Using LLMs for item creation: Validating the potential of au
 tomatically generated sentence repetition test items for language assessme
 nt (Sarah Löber\, Björn Rudzewitz\, Yuan Chu\, Mengyuan He\, Shiqin Liu\, 
 Yushan Ye\, Xiaobin Chen)\n- FinnGEC: Benchmarking Grammatical Error Corre
 ction for Finnish (Anh-Duc Vu\, Mikhail Zolotilin\, Jue Hou\, Anisia Katin
 skaia\, Yiheng Wu\, Roman Yangarber)\n- From Metrics to Meaning: Rule-Grou
 nded LLM Explanations for Data Literacy in the Case of Youth Football (Tom
 asz Piłka\, Tomasz Kuczyński\, Mateusz Czajka)\n- Classification of Studen
 t Struggle in Mathematics (Hannah Levin\, Madhura Padwal\, Nchimunya Mwiin
 ga)\n- Data-lean fine-tuning of models for evaluating teacher performance 
 in a GenAI-led elicitation simulation (Beata Beigman Klebanov\, Andrew Hoa
 ng\, Jamie Mikeska\, Benny Longwill\, Sanjna Kashyap\, Shreyashi Halder\, 
 Aakanksha Bhatia)\n- Multi-component student writing profiles for expert-a
 ligned automated evaluation of English learner essays. (Russell Moore\, An
 drew Caines\, Paula Buttery)\n- Noise Steering for Controlled Text Generat
 ion: Improving Diversity and Reading-Level Fidelity in Arabic Educational 
 Story Generation (Haziq Khalid\, Salsabeel Shapsough\, Imran Zualkernan)\n
 - Rubrics as Semantic Subspaces: A Unified Approach to Rubric-based Constr
 ucted Response Scoring across Short Answers and Essays (Sebastian Gombert\
 , Sonja Hahn\, Nico Andersen\, Leon Camus\, Zhifan Sun\, Ngoc Nhu Hao Nguy
 en\, Fabian Zehner\, Longwei Cong\, Alexander Mehler\, Hendrik Drachsler)\
 n- PeerMathDial: A Middle School Dialogue Dataset for Student Collaborativ
 e Math Problem Solving (Murong Yue\, Desmond Mcglone\, Emily Slutz\, Wenha
 n Lyu\, Yixuan Zhang\, Jennifer Suh\, Ziyu Yao)\n- Evaluating LLM-Generate
 d Formative Feedback for Undergraduate Mathematics Through the Lens of Fee
 dback Theory (Aron Gohr\, Marie-Amelie Lawn\, Kevin Gao\, Inigo Serjeant\,
  Stephen Heslip)\n- Retrieval-Augmented Tutoring for Algorithm Tracing and
  Problem-Solving in AI Education (Mragisha Jain\, Tirth Bhatt\, Griffin Pi
 tts\, Aum Pandya\, Peter Brusilovsky\, Narges Norouzi\, Arto Hellas\, Juho
  Leinonen\, Bita Akram)\n- Edit-level Majority Voting Mitigates Over-Corre
 ction in LLM-based Grammatical Error Correction (Takumi Goto\, Yusuke Saka
 i\, Taro Watanabe)\n- Toward Cross-Domain Automated Feedback: A Comparativ
 e Evaluation of Open-Source Models across Diverse Student Assessment Types
  (Muhammad Haseeb\, Min Paing Hmue\, Ahmad Imam Amjad\, Maaz Amjad\, Victo
 r Sheng)\n- AIDA at BEA 2026 Shared Task 1: A Two-Stage Framework for L1-A
 ware Vocabulary Difficulty Prediction with Representation Diversity and Re
 sidual Calibration (Seok Hyeon Cho\, JunHyeok Choi\, Sangeun Ji\, Sung Won
  Han)\n- BoostedCats at BEA 2026 Shared Task 1: What Makes a Word Hard to 
 Learn? Modeling L1 Influence on English Vocabulary Difficulty (Jonas Mayer
  Martins\, Zhuojing Huang\, Aaricia Herygers\, Lisa Beinborn)\n- uogal at 
 BEA 2026 Shared Task 1: Ensemble of Multilingual Encoders with NMT Augment
 ation for L1-Aware Vocabulary Difficulty Prediction (bernardo stearns\, Jo
 hn P. McCrae\, Thomas Gaillat\, Jefkine Kafunah)\n- IWM-DKM at BEA 2026 Sh
 ared Task 2: Supplementing Supervised Fine-Tuning for Rubric-Based Short A
 nswer Scoring (Kate Belcher\, Marius De Kuthy Meurers\, Kordula De Kuthy\,
  Detmar Meurers)\n- RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting 
 in Rubric-based Scoring for German (Ignacio Sastre\, Ignacio Remersaro\, F
 acundo Díaz\, Nicolás De Horta\, Luis Chiruzzo\, Aiala Rosá\, Santiago Gón
 gora)\n- UOL@IDEM at BEA 2026 Shared Task 1: Neural Fusion and Feature-Ric
 h Modeling for L1-Aware Vocabulary Difficulty Prediction (Nouran Khallaf\,
  Serge Sharoff)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-c51019a1-e747-4f0d-adcb-bc9d58d87e85
DTSTART;TZID=America/Los_Angeles:20260704T153000
DTEND;TZID=America/Los_Angeles:20260704T160000
SUMMARY:BEA 2026: Coffee Break
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-1c7e797d-e98f-48cd-95e6-ea19655c6464
DTSTART;TZID=America/Los_Angeles:20260704T160000
DTEND;TZID=America/Los_Angeles:20260704T164500
SUMMARY:BEA 2026: Panel
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Transitioning from Academia to the EdTech Industry\n(Christine 
 Bagarino\, Kai North\, Keelan Evanini\, Mariano Felice)
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-08d0d35d-00f2-4c56-8a0c-a2345bc1fc3c
DTSTART;TZID=America/Los_Angeles:20260704T164500
DTEND;TZID=America/Los_Angeles:20260704T171500
SUMMARY:BEA 2026: Oral Session D
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-86962713-bfcc-4359-a3d6-1c41c0c9e85c
DTSTART;TZID=America/Los_Angeles:20260704T164500
DTEND;TZID=America/Los_Angeles:20260704T170000
SUMMARY:Incentives Of EdTech: A Systematic Review Of EduNLP Research
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Gabrielle Gaudeau\, Aoife O'Driscoll\, Jasper Degraeuwe
 \, Andrew Caines\, Donya Rooein\, Zeerak Talat
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-3a5170f6-4887-40f9-bd69-0507e62cd7eb
DTSTART;TZID=America/Los_Angeles:20260704T170000
DTEND;TZID=America/Los_Angeles:20260704T171500
SUMMARY:Effects of Varying LLM Access on Essay Writing Behavior
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
DESCRIPTION:Talk by Julia Christenson\, Karin de Langis\, Shirley Anugrah H
 ayati\, Dongyeop Kang
CATEGORIES:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260629T103615Z
UID:TS1-2c8be96d-128e-4e95-aca9-17cd526cef15
DTSTART;TZID=America/Los_Angeles:20260704T171500
DTEND;TZID=America/Los_Angeles:20260704T173000
SUMMARY:BEA 2026: Closing Remarks
LOCATION:Harbor D\nZoom\nhttps://underline.io/events/530/sessions?eventSess
 ionId=22998
CATEGORIES:
END:VEVENT
END:VCALENDAR