Educational Dialogue Systems

Follow this topic Ask about this topic

Latest papers

21 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them
Oct 16, 2026Ziqi Liu, Ruiwei Xiao, Yuxuan Li +1Educational Dialogue Systems AI in Education
Carnegie Mellon University
Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing
Sep 1, 2026Alexandre Clin Deffarges, Nataliya Kosmyna, Pattie MaesIntelligent Tutoring Systems AI in Education
ETH Zürich · MIT Media Lab
PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise
Aug 3, 2026Abdulrahman AlRabah, Xiaocheng Yang, Dilek Hakkani-Tür +1Human-AI Decision Making AI-Assisted Decision Making
University of Illinois Urbana-Champaign
Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor Models
Jul 30, 2026Shuyi Fan, Boyuan Deng, Mengyu Xu +4LLM Evaluation LLM-as-a-Judge
Columbia University, USA · Johns Hopkins University, USA · The University of Chicago, USA +4
Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning
Jul 25, 2026Xiaokun Wang, Siyu Song, Wentao Liu +1LLM Alignment Intelligent Tutoring Systems
East China Normal University, Shanghai, China · Shanghai Chuangjie Situo Information Technology Co., Ltd., Shanghai, China · Shanghai Normal University, Shanghai, China +1
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
Jul 9, 2026Kristina Schaaff, Quintus Stierstorfer, Valerie HekkelHigher Education AI in Education
IU International University of Applied Sciences, Erfurt, Germany.
Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
Jun 18, 2026Po-Chin Chang, Nicholas Hogan, Aske Plaat +1Prompt Learning Intelligent Tutoring Systems
Leiden University · FutureWhiz
Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wild
Jun 10, 2026Sidney Tio, Arunesh Sinha, Pradeep VarakanthamIntelligent Tutoring Systems AI in Education
School of Computing and Information Systems Singapore Management University · Department of Management Science and Information Systems Rutgers Business School
RPO-PDT: Demonstrating Role-Play-Based Knowledge Adaptation for Student Support Dialogue (Demonstration System)
Jun 8, 2026Filip Janik, Ewa Olton, Robert Smales +4AI in Education Educational Dialogue Systems
Edinburgh Napier University
GRADE: Generalizable Reasoning-Aware Dialogue Evaluation for AI Tutors
May 27, 2026Parth Bhalerao, Jeromy Chang, David Chou +1Intelligent Tutoring Systems Low-Rank Adaptation
Santa Clara University
From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages
May 21, 2026Siddhant Hitesh Mantri, Dhara Gorasiya, Malhar Kulkarni +1Knowledge Augmentation for Language Models Educational Dialogue Systems
NMIMS, Mumbai · CFILT, IIT Bombay
PromptDecipher: Supporting AI Tutor Authoring Through Editable Simulated Interactions
May 15, 2026Miina Koyama, Ruiwei Xiao, John StamperHuman-AI Interaction LLM Prompting
Carnegie Mellon University Pittsburgh, Pennsylvania, USA
Adesua: Development and Feasibility Study of an AI WhatsApp Bot for Science Learning in West Africa
May 14, 2026George Boateng, Evans Atompoya, Philemon Badu +4Educational Technology AI in Education
ETH Zurich, Switzerland · Kwame AI Inc., U.S. · Charité - Universitätsmedizin Berlin, Germany
RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking
May 12, 2026Leyi Li, Chenyu Du, Jiafei Sun +2Computer Science Education AI in Education
Xi’an Jiaotong-Liverpool University · Suzhou, Jiangsu, China
Your Students Don't Use LLMs Like You Wish They Did
Apr 26, 2026Sebastian Kobler, Matthew Clemson, Angela Sun +1Educational Assessment AI in Education
The University of Sydney
Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
Apr 24, 2026Zhilin Fan, Deliang Wang, Penghe Chen +1Explainable Artificial Intelligence AI in Education
School of Educational Technology, Beijing Normal University, Beijing, China · Faculty of Education, The University of Hong Kong, Hong Kong SAR, China · Advanced Innovation Center for Future Education, Beijing Normal University, Beijing, China
Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
Apr 3, 2026Jinsook Lee, Kirk Vanacore, Zhuqian Zhou +2LLM-Assisted Annotation Retrieval-Augmented ICL
Cornell University Ithaca, NY, 14850, USA
Impact of Multimodal and Conversational AI on Learning Outcomes and Experience
Apr 2, 2026Karan Taneja, Anjali Singh, Ashok K. GoelEducational Dialogue Systems AI in Education
Georgia Institute of Technology, Atlanta GA 30332, USA · University of Texas at Austin, Austin TX 78712, USA
TeachingCoach: A Fine-Tuned Scaffolding Chatbot for Instructional Guidance to Instructors
Mar 18, 2026Isabel Molnar, Peiyu Li, Si Chen +5Educational Dialogue Systems Educational Technology
University of Notre Dame Notre Dame, Indiana, USA
Hybrid LLM-Embedded Dialogue Agents for Learner Reflection: Designing Responsive and Theory-Driven Interactions
Feb 24, 2026Paras Sharma, YuePing Sha, Janet Shufor Bih Epse Fofang +6Self-Regulated Learning Educational Dialogue Systems
University of Pittsburgh Pittsburgh, Pennsylvania, USA · Carnegie Mellon University Pittsburgh, Pennsylvania, USA · Bowie State University Bowie, Maryland, USA
"How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations
Feb 20, 2026Alexandra Neagu, Marcus Messer, Peter Johnson +1Generative AI in Education Educational Dialogue Systems
Imperial College London, London, United Kingdom

Oct 16, 2026J/K move · Enter open · S save

EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them

Ziqi Liu, Ruiwei Xiao, Yuxuan Li, John Stamper

Carnegie Mellon University

Educational Dialogue Systems AI in Education Instruction Following Prompt Engineering

Open paper AskPDF arXiv

Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introduce EduWild, a dataset of 1,726 conversations with 217 teacher-configured chatbots, each paired with the instructions and configuration behind it, including 900 conversations from the intended end users of 35 deployed chatbots. We develop a 29-code taxonomy covering factual, workflow, diagnostic, and pedagogical failures and apply it using a human-calibrated LLM judge. The most frequent failures are lapses in following teacher intent --- bots skip required workflow steps (53.8% of end-user conversations), omit expectation setup (33.4%), and overload learners with information or questions (37.1%). Guided by these findings, we design a prompt-based harness targeting the six most frequent failure modes. In a study with 200 college students across ten bots, the harness reduces the mean number of target failure codes per conversation from 1.406 to 0.489, a 65.2% relative reduction with bots weighted equally. These findings show how real-world failure analysis can guide practical improvements to educational chatbots.