---
title: "BEA 2026 — all accepted papers with summaries and citations"
description: "All 92 papers of BEA 2026, the most cited first; those with our summary link to it. Among them: A Survey of Automated Presentation Coaching…"
canonical: "https://research.elamur.ai/free/en/venues/bea/2026/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/bea/2026/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [BEA](https://md.research.elamur.ai/free/en/venues/bea/) / [2026](https://md.research.elamur.ai/free/en/venues/bea/2026/) / papers

# BEA 2026: all accepted papers

92 papers · the most cited first · [← BEA 2026](https://md.research.elamur.ai/free/en/venues/bea/2026/)

1. **[A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges ↗](https://aclanthology.org/2026.bea-1.4/)**Wen Liang, Li Siyan, Zackary Rackauckas et al.*1 citation*
2. **[Evaluating Adaptive Personalization of Educational Readings with Simulated Learners ↗](https://aclanthology.org/2026.bea-1.63/)**Ryan T. Woo, Anmol Rao, Aryan Keluskar et al.*1 citation*
3. **[Evaluating LLM Workflows for Generating Clinical Communication Assessment Items: A Comparative Study with Subject-Matter Experts ↗](https://aclanthology.org/2026.bea-1.12/)**Christopher Runyon, Peter Baldwin, Ian Micir et al.*1 citation*
4. **[A Bigger Catch: Fine-Grained Curriculum Standards Alignment on the MathFish Benchmark ↗](https://aclanthology.org/2026.bea-1.15/)**Xinman Liu, Mayank Sharma, Xinyu Shi
5. **[AIDA at BEA 2026 Shared Task 1: A Two-Stage Framework for L1-Aware Vocabulary Difficulty Prediction with Representation Diversity and Residual Calibration ↗](https://aclanthology.org/2026.bea-1.72/)**Seok Hyeon Cho, JunHyeok Choi, Sangeun Ji et al.
6. **[AMATI at BEA 2026 Shared Task 2: Automatic Short Answer Grading with Inductive Logic Programming and a Large Language Model ↗](https://aclanthology.org/2026.bea-1.89/)**Alistair Willis, Aisling Third
7. **[ASLAN at BEA 2026 Shared Task 2: Voting Across Scoring Paradigms ↗](https://aclanthology.org/2026.bea-1.87/)**Marie Bexte, Yuning Ding, Josef Ruppenhofer et al.
8. **[Assessing the Quality and Consistency of Automated Knowledge Component Generation using Instructor-generated Questions and LLMs ↗](https://aclanthology.org/2026.bea-1.18/)**Jordan Esiason, Priyanka Khare, Wookhee Min et al.
9. **[Assessment of L2 speech global dimensions using large audio language models ↗](https://aclanthology.org/2026.bea-1.49/)**Elsayed Issa, Mahmoud Ali
10. **[BoostedCats at BEA 2026 Shared Task 1: What Makes a Word Hard to Learn? Modeling L1 Influence on English Vocabulary Difficulty ↗](https://aclanthology.org/2026.bea-1.74/)**Jonas Mayer Martins, Zhuojing Huang, Aaricia Herygers et al.
11. **[Challenges in Machine Translation of Interactive Multimodal Exercises ↗](https://aclanthology.org/2026.bea-1.11/)**Lucie Polakova, Miroslav Hrabal, Věra Kloudová et al.
12. **[Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety](https://md.research.elamur.ai/free/en/papers/shen-2026-children-s-english-reading-story/)**Qian Shen, Fanghua Cao, Min Yao et al.*our summary*
13. **[Classification of Student Struggle in Mathematics ↗](https://aclanthology.org/2026.bea-1.36/)**Hannah Levin, Madhura Padwal, Nchimunya Mwiinga
14. **[Comparative Evaluation of AI-Generated vs. Expert-written Answer Explanations for a Medical Education Self-Assessment ↗](https://aclanthology.org/2026.bea-1.31/)**Yiyun Zhou, Francis O'Donnell, Victoria Yaneva
15. **[Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most ↗](https://aclanthology.org/2026.bea-1.56/)**Tahreem Yasir, Wenbo Li, Sam Gilson et al.
16. **[Criterial Features in German: Towards Interpretable NLP in Readability Assessment ↗](https://aclanthology.org/2026.bea-1.6/)**Denise Loefflad, Sofia Kathmann, Heiko Holz et al.
17. **[Data Asgardians at BEA 2026 Shared Task 1: A Hybrid Transformer–Feature Ensemble for L1-Aware English Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.82/)**Adrian Pineda, Sabur Butt, Héctor Ceballos Cancino
18. **[Data-lean fine-tuning of models for evaluating teacher performance in a GenAI-led elicitation simulation ↗](https://aclanthology.org/2026.bea-1.38/)**Beata Beigman Klebanov, Andrew Hoang, Jamie Mikeska et al.
19. **[Domain-Adaptive Pre-training for Automated Short Answer Grading in Conceptual Physics: Reliability, Question-Level Analysis, and Error Reduction ↗](https://aclanthology.org/2026.bea-1.45/)**Shirin Lade, Alistair Willis, Jonathan Nylk et al.
20. **[Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction ↗](https://aclanthology.org/2026.bea-1.60/)**Takumi Goto, Yusuke Sakai, Taro Watanabe
21. **[EduMUSE: A Multimodal Educational Dataset with Automatically Extracted Instructional Context ↗](https://aclanthology.org/2026.bea-1.25/)**Andreea Dutulescu, Stefan Ruseti, Mihai Dascalu et al.
22. **[EduNLP at BEA 2026 Shared Task 1: Multi-Model Ensemble with Feature-Augmented Transformers for Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.71/)**Avinash Kumar Sharma
23. **[Effects of Varying LLM Access on Essay Writing Behavior ↗](https://aclanthology.org/2026.bea-1.48/)**Julia Christenson, Karin de Langis, Shirley Anugrah Hayati et al.
24. **[Estimating LLM Grading Ability and Response Difficulty in Automatic Short Answer Grading via Item Response Theory ↗](https://aclanthology.org/2026.bea-1.19/)**Longwei Cong, Sonja Hahn, Sebastian Gombert et al.
25. **[Evaluating LLM-Generated Formative Feedback for Undergraduate Mathematics Through the Lens of Feedback Theory ↗](https://aclanthology.org/2026.bea-1.55/)**Aron Gohr, Marie-Amelie Lawn, Kevin Gao et al.
26. **[Failure at BEA 2026 Shared Task 1: One Pipeline, Three L1s: A Unified Language-Agnostic System for Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.73/)**Abid Al Hossain, Kamruzzaman Khan Alve
27. **[Findings of the BEA 2026 Shared Task on Vocabulary Difficulty Prediction for English Learners ↗](https://aclanthology.org/2026.bea-1.65/)**Mariano Felice, Lucy Skidmore
28. **[Fine-Grained Content Zone Prediction in German Argumentative Essays Using LLMs ↗](https://aclanthology.org/2026.bea-1.27/)**Xiaoyu Bai, Manfred Stede
29. **[FinnGEC: Benchmarking Grammatical Error Correction for Finnish ↗](https://aclanthology.org/2026.bea-1.33/)**Anh-Duc Vu, Mikhail Zolotilin, Jue Hou et al.
30. **[From Dialogue to Learner Modeling: Identifying Candidate Signals of Productive Use in LLM-Based Grammar Practice ↗](https://aclanthology.org/2026.bea-1.62/)**Luisa Ribeiro-Flucht, Lanhua Huang, Xiaobin Chen
31. **[From Metrics to Meaning: Rule-Grounded LLM Explanations for Data Literacy in the Case of Youth Football ↗](https://aclanthology.org/2026.bea-1.34/)**Tomasz Piłka, Tomasz Kuczyński, Mateusz Czajka
32. **[From Questions to Assessment Tuples: A Multi-Agent Framework with Bloom-Specialized Agents and Automated Verification ↗](https://aclanthology.org/2026.bea-1.22/)**Gee-Lyle Wong, Runcong Zhao, Yulan He et al.
33. **[Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment ↗](https://aclanthology.org/2026.bea-1.54/)**Grandee Lee, Yue Wang, Che Yee Lye et al.
34. **[Glite at BEA 2026 Shared Task 1: Holistic Difficulty Models Dominate, Feature Engineering Closes the Gap in L1-Aware Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.77/)**Vassili Philippov, Dmitrii Andreev, Pavel Katunin et al.
35. **[HFT at BEA 2026 Shared Task 2: Blunt-Edge Models for Hybrid Grading ↗](https://aclanthology.org/2026.bea-1.86/)**Ulrike Pado
36. **[IWM-DKM at BEA 2026 Shared Task 2: Supplementing Supervised Fine-Tuning for Rubric-Based Short Answer Scoring ↗](https://aclanthology.org/2026.bea-1.90/)**Kate Belcher, Marius De Kuthy Meurers, Kordula De Kuthy et al.
37. **[Incentives Of EdTech: A Systematic Review Of EduNLP Research ↗](https://aclanthology.org/2026.bea-1.50/)**Gabrielle Gaudeau, Aoife O'Driscoll, Jasper Degraeuwe et al.
38. **[Inferring Student Engagement via Real-Time Thermal–Visual Voice Activity Detection ↗](https://aclanthology.org/2026.bea-1.2/)**Bradley Goodman
39. **[Instruction-Following LLMs for Grammatical Error Correction: Analyzing Neutral-Anchored Instructional Sensitivity Across Editing Modes ↗](https://aclanthology.org/2026.bea-1.17/)**Tolgahan Türker, Gülşen Eryiğit
40. **[Intent vs. Surface: Recovering Acoustic Realization from Modern ASR for Pronunciation Training ↗](https://aclanthology.org/2026.bea-1.23/)**Seongjin Park
41. **[Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues ↗](https://aclanthology.org/2026.bea-1.43/)**Shuyan Huang, Alexander Scarlatos, Jaewook Lee et al.
42. **[Investigating Context-aware CTC for Pronunciation Assessment: Mitigating Peaky Behavior and Context Independency Assumption ↗](https://aclanthology.org/2026.bea-1.3/)**Jiun-Ting Li, Tien-Hong Lo, Bi-Cheng Yan et al.
43. **[Jinnie's Lab at BEA 2026 Shared Task 1: Precalibration of Vocabulary Item Difficulty with Multilingual Transformers and Multi-Task Learning ↗](https://aclanthology.org/2026.bea-1.76/)**Zhe Li, Pauline Aguinalde, Jinnie Shin
44. **[KEYSCORE –- Keystroke-enhanced Automated Essay Scoring ↗](https://aclanthology.org/2026.bea-1.24/)**Nils-Jonathan Schaller, Daniel Mora Melanchthon, Thorben Jansen et al.
45. **[Kelvi: A Morphological Parser to Support Tamil Literacy ↗](https://aclanthology.org/2026.bea-1.21/)**Shankhalika Srikanth, Sabrina Yu, Sophia Chan et al.
46. **[LLM-Powered but Rule-Grounded: Pedagogically Relevant Grammatical Error Characterization for Learner Model Construction ↗](https://aclanthology.org/2026.bea-1.58/)**Soroosh Akef, Amália Mendes, Patrick Rebuschat et al.
47. **[Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization ↗](https://aclanthology.org/2026.bea-1.7/)**Jaewook Lee, Alexander Scarlatos, Simon Woodhead et al.
48. **[Measuring Optimal Challenge: Trajectory-Based Difficulty Alignment in Open-Ended Language Tutoring ↗](https://aclanthology.org/2026.bea-1.46/)**Ziqi Shu, Shuman Wang, Michael Hardy
49. **[Multi-component student writing profiles for expert-aligned automated evaluation of English learner essays. ↗](https://aclanthology.org/2026.bea-1.39/)**Russell Moore, Andrew Caines, Paula Buttery
50. **[Multi-step Large Language Model for Fine-Grained Feedback in Stepwise Linear Equation Solutions ↗](https://aclanthology.org/2026.bea-1.28/)**Imran Chamieh, Torsten Zesch, Klaus Giebermann
51. **[NLP-Explorers at BEA 2026 Shared Task 1: DeBERTa–CatBoost Weighted Ensemble Approach for L1-Specific Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.78/)**Tayyab Latif, Asifa Bibi, Sabur Butt et al.
52. **[Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation ↗](https://aclanthology.org/2026.bea-1.41/)**Haziq Khalid, Salsabeel Shapsough, Imran Zualkernan
53. **[Opportunities and Challenges of LLMs in Education: An NLP Perspective ↗](https://aclanthology.org/2026.bea-1.26/)**Sowmya Vajjala, Bashar Alhafni, Stefano Banno et al.
54. **[PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs ↗](https://aclanthology.org/2026.bea-1.37/)**Ravi Kumar, Utkarsh Grover, Xiaomin Lin et al.
55. **[PeerMathDial: A Middle School Dialogue Dataset for Student Collaborative Math Problem Solving ↗](https://aclanthology.org/2026.bea-1.47/)**Murong Yue, Desmond Mcglone, Emily Slutz et al.
56. **[Policy-Sensitive Fairness Evaluation in Automated Scoring of Clinical Communication ↗](https://aclanthology.org/2026.bea-1.40/)**Saed Rezayi, Le An Ha, Victoria Yaneva et al.
57. **[Predicting Item Difficulty and Generating Reading Comprehension Items via an Annotated Repository ↗](https://aclanthology.org/2026.bea-1.53/)**Radhika Kapoor, Mayank Sharma, Sang Truong et al.
58. **[Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation ↗](https://aclanthology.org/2026.bea-1.29/)**Abigail Gurin Schleifer, Moriah Ariely, Beata Beigman Klebanov et al.
59. **[RABIT: Rationale-Based Distillation Towards Interpretable Automatic Speaking Assessment via a Small Language Model ↗](https://aclanthology.org/2026.bea-1.9/)**Bi-Cheng Yan, Hong-Yun Lin, Fu-An Chao et al.
60. **[RETUYT-INCO at BEA 2026 Shared Task 1: Feature-Enriched mDeBERTa for Word Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.79/)**Santiago Robaina, Aiala Rosá, Luis Chiruzzo
61. **[RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting in Rubric-based Scoring for German ↗](https://aclanthology.org/2026.bea-1.91/)**Ignacio Sastre, Ignacio Remersaro, Facundo Díaz et al.
62. **[Report on the BEA 2026 Shared Task on Rubric-based Short Answer Scoring for German ↗](https://aclanthology.org/2026.bea-1.85/)**Sebastian Gombert, Zhifan Sun, Fabian Zehner et al.
63. **[Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education ↗](https://aclanthology.org/2026.bea-1.57/)**Mragisha Jain, Tirth Bhatt, Griffin Pitts et al.
64. **[Rubrics as Semantic Subspaces: A Unified Approach to Rubric-based Constructed Response Scoring across Short Answers and Essays ↗](https://aclanthology.org/2026.bea-1.44/)**Sebastian Gombert, Sonja Hahn, Nico Andersen et al.
65. **[SAAKTH at BEA 2026 Shared Task 1: L1-Aware English Vocabulary Difficulty Prediction with Hybrid Transformer and Psycholinguistic Features ↗](https://aclanthology.org/2026.bea-1.69/)**Karthik Mattu, Adit Dhall, Arshad Naguru et al.
66. **[SATLab at BEA 2026 Shared Task 1: Predicting the Difficulty of English Words for Three L1 Learners Using Primarily Psycholinguistic Features ↗](https://aclanthology.org/2026.bea-1.66/)**Yves Bestgen
67. **[SDPA at BEA 2026 Shared Task 2: Efficient LLM Fine-Tuning for Rubric-based Short Answer Scoring ↗](https://aclanthology.org/2026.bea-1.92/)**Zhexiong Liu, Jing Zhang
68. **[Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult? ↗](https://aclanthology.org/2026.bea-1.84/)**Adam Nohejl, Xuanxin Wu, Yusuke Ide et al.
69. **[Sharing is Caring: Advantages of Sharing a Language Background with Learners as an Annotator of Learner Data in UD ↗](https://aclanthology.org/2026.bea-1.35/)**Caroline Grand-Clement, Arianna Masciolini
70. **[SurreyCTS at BEA 2026 Shared Task 1: Semantic Funnelling and Entropy-based Multilingual Lexical Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.70/)**Georgina Willoughby, Jordan Painter, Diptesh Kanojia et al.
71. **[TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling ↗](https://aclanthology.org/2026.bea-1.81/)**Wicaksono Leksono Muhamad, Joanito Agili Lopo, Tsamarah Rana Nugraha et al.
72. **[Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation ↗](https://aclanthology.org/2026.bea-1.59/)**Mariam Barakat, Ekaterina Kochmar
73. **[TeamXBC at BEA 2026 Shared Task 1: How AI (and I) won the shared task: Vibe and agentic coding solutions for practical machine learning problems ↗](https://aclanthology.org/2026.bea-1.68/)**Xiaobin Chen
74. **[The Aftermath of DrawEduMath: Vision Language Models Underperform with Struggling Students and Misdiagnose Errors ↗](https://aclanthology.org/2026.bea-1.5/)**Li Lucy, Albert Zhang, Nathan Anderson et al.
75. **[The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance ↗](https://aclanthology.org/2026.bea-1.42/)**Tsvetomila Mihaylova, Evanfiya Logacheva, Arto Hellas et al.
76. **[Theory of Mind and Application in Educational Context ↗](https://aclanthology.org/2026.bea-1.1/)**Effat Farhana, Maha Zainab, Qiaosi Wang et al.
77. **[Through the Sentence Lens: Explainable Essay Scoring through Fine-Grained Predictions ↗](https://aclanthology.org/2026.bea-1.16/)**Daniel Mora Melanchthon, Stefan Keller, Andrea Horbach
78. **[Token Titans at BEA 2026 Shared Task 1: Multilingual Lexical Complexity Prediction via Fine-Tuned XLM-RoBERTa with Ensemble Decoding ↗](https://aclanthology.org/2026.bea-1.80/)**Anubhab Parashar, Sandeep Mathias
79. **[Toward Cross-Domain Automated Feedback: A Comparative Evaluation of Open-Source Models across Diverse Student Assessment Types ↗](https://aclanthology.org/2026.bea-1.64/)**Muhammad Haseeb, Min Paing Hmue, Ahmad Imam Amjad et al.
80. **[Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning via Knowledge-Grounded LLM ↗](https://aclanthology.org/2026.bea-1.8/)**Younghun Lee, Amir Bralin, Nobel Sanjay Rebello et al.
81. **[Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation ↗](https://aclanthology.org/2026.bea-1.10/)**Kseniia Petukhova, Tien Dat Nguyen, Ekaterina Kochmar
82. **[Towards Self-Referential Analytic Assessment: A Profile-Based Approach to L2 Writing Evaluation with LLMs ↗](https://aclanthology.org/2026.bea-1.13/)**Stefano Banno, Kate Knill, Mark Gales
83. **[Transformer-based readability classifiers are worse than you think: Evidence from cross-domain Arabic readability assessment ↗](https://aclanthology.org/2026.bea-1.52/)**Sarah Alzubi, Robert Reynolds
84. **[UGA Threshold at BEA 2026 Shared Task 1: Predicting Vocabulary Acquisition Difficulty with Hand-Crafted SLA-Based Features ↗](https://aclanthology.org/2026.bea-1.67/)**Emma Dalbo
85. **[UOL@IDEM at BEA 2026 Shared Task 1: Neural Fusion and Feature-Rich Modeling for L1-Aware Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.83/)**Nouran Khallaf, Serge Sharoff
86. **[Using Interaction Log Data to Evaluate and Improve Feedback Accuracy in an Intelligent Language Tutoring System ↗](https://aclanthology.org/2026.bea-1.14/)**Mariia Soliar, Leona Colling, Stephen Bodnar et al.
87. **[Using LLMs for item creation: Validating the potential of automatically generated sentence repetition test items for language assessment ↗](https://aclanthology.org/2026.bea-1.30/)**Sarah Löber, Björn Rudzewitz, Yuan Chu et al.
88. **[Using k-Shot Prompting with Large k for the Automated Scoring of a German Written Elicited Imitation Test ↗](https://aclanthology.org/2026.bea-1.20/)**Malte Sternik, Ronja Laarmann-Quante, Anastasia Drackert
89. **[WSE Research at BEA 2026 Shared Task 2: Multi-Strategy Rubric-Based Short Answer Scoring for German ↗](https://aclanthology.org/2026.bea-1.88/)**Jonas Gwozdz, Andreas Both
90. **[What Aggregate Scores Hide: Per-Rule Evaluation of Russian Grammatical Error Correction ↗](https://aclanthology.org/2026.bea-1.32/)**Anna Smirnova, Artyom Kopan, Vladislav Makeev et al.
91. **[Zero Shot Phonics: Evaluating Constraint-Adherent Phonics Story Generation in Large Language Models ↗](https://aclanthology.org/2026.bea-1.61/)**Maria Monica Manlises, Ethel Ong
92. **[uogal at BEA 2026 Shared Task 1: Ensemble of Multilingual Encoders with NMT Augmentation for L1-Aware Vocabulary Difficulty Prediction ↗](https://aclanthology.org/2026.bea-1.75/)**Bernardo Stearns, John P. McCrae, Thomas Gaillat et al.
- [← back to](https://md.research.elamur.ai/free/en/venues/bea/2026/) — BEA 2026