{"total":21,"rows":[{"id":"2308.02773","title":"EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education","created":"2023-08-05","cited_by_count":80,"area":null},{"id":"2412.09416","title":"Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors","created":"2024-12-12","cited_by_count":61,"area":null},{"id":"2502.18940","title":"MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors","created":"2025-02-26","cited_by_count":49,"area":null},{"id":"2507.10579","title":"Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors","created":"2025-07-11","cited_by_count":18,"area":null},{"id":"2307.04274","title":"Assessing the efficacy of large language models in generating accurate teacher responses","created":"2023-07-09","cited_by_count":6,"area":null},{"id":"2507.22753","title":"Opportunities and Challenges of LLMs in Education: An NLP Perspective","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2510.22581","title":"Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems","created":"2025-10-26","cited_by_count":5,"area":null},{"id":"2507.06910","title":"Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues","created":"2025-07-09","cited_by_count":4,"area":null},{"id":"2404.15104","title":"Identifying Fairness Issues in Automatically Generated Testing Content","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2506.11243","title":"RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2506.01817","title":"BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2510.23011","title":"LangLingual: A Personalised, Exercise-oriented English Language Learning Tool Leveraging Large Language Models","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.03688","title":"AITutor-EvalKit: Exploring the Capabilities of AI Tutors","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2604.23486","title":"Your Students Don't Use LLMs Like You Wish They Did","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2403.15426","title":"CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2408.08805","title":"CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2501.06728","title":"Measuring the Robustness of Reference-Free Dialogue Evaluation Systems","created":"2025-01-12","cited_by_count":0,"area":null},{"id":"2601.21375","title":"TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2607.23322","title":"IKS-Instruct: A 24,000-Example Multilingual Dataset for Teaching Language Models Indian Knowledge Systems","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.12949","title":"EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}