{"total":52,"rows":[{"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":"2410.03017","title":"Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise","created":"2024-10-03","cited_by_count":50,"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":"2409.16490","title":"Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs","created":"2024-09-24","cited_by_count":46,"area":null},{"id":"2503.06424","title":"Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues","created":"2025-03-09","cited_by_count":43,"area":null},{"id":"2407.09136","title":"Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors","created":"2024-07-12","cited_by_count":41,"area":"lr"},{"id":"2410.03781","title":"Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure","created":"2024-10-03","cited_by_count":24,"area":null},{"id":"2502.13311","title":"Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors","created":"2025-02-18","cited_by_count":20,"area":"agents"},{"id":"2505.19997","title":"Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents","created":"2025-05-26","cited_by_count":19,"area":"agents"},{"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":"2505.15607","title":"From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2406.11709","title":"Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging","created":"2024-06-17","cited_by_count":14,"area":null},{"id":"2410.04253","title":"Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills","created":"2024-10-05","cited_by_count":14,"area":null},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2405.04495","title":"Toward In-Context Teaching: Adapting Examples to Students' Misconceptions","created":"2024-05-07","cited_by_count":12,"area":null},{"id":"2505.16931","title":"PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2501.07244","title":"Can Vision-Language Models Evaluate Handwritten Math?","created":"2025-01-13","cited_by_count":10,"area":"mllm"},{"id":"2411.03495","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2503.04804","title":"What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2506.07626","title":"Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2409.11917","title":"LLMs in Education: Novel Perspectives, Challenges, and Opportunities","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2604.18660","title":"Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks","created":"2026-04-20","cited_by_count":7,"area":null},{"id":"2502.14767","title":"Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis","created":"2025-02-20","cited_by_count":6,"area":"lr"},{"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":"2508.06583","title":"Discerning minds or generic tutors? Evaluating instructional guidance capabilities in Socratic LLMs","created":"2025-08-08","cited_by_count":5,"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":"2505.18549","title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2506.05579","title":"When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration","created":"2025-06-05","cited_by_count":4,"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":"2506.04920","title":"Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2508.11184","title":"Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2506.13037","title":"MAGIC: Multi-Agent Argumentation and Grammar Integrated Critiquer","created":"2025-06-16","cited_by_count":2,"area":"agents"},{"id":"2406.05603","title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2505.15596","title":"Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.10627","title":"NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI Tutors","created":"2025-06-12","cited_by_count":1,"area":"rag"},{"id":"2508.11052","title":"AI That Helps Us Help Each Other: A Proactive System for Scaffolding Mentor-Novice Collaboration in Entrepreneurship Coaching","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.17961","title":"Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2606.30578","title":"Uncertainty-Aware Generation and Decision-Making Under Ambiguity","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.01591","title":"StudentSim: Training LLM-based Student Simulators","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2507.05385","title":"EduCoder: An Open-Source Annotation System for Education Transcript Data","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2509.02855","title":"IDEAlign: Comparing Ideas of Large Language Models to Domain Expert","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.12899","title":"EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpus","created":"2025-10-14","cited_by_count":0,"area":"distill"},{"id":"2511.22883","title":"FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writing","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.20780","title":"Large Language Models Approach Expert Pedagogical Quality in Math Tutoring but Differ in Instructional and Linguistic Profiles","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.24375","title":"Towards Reward Modeling for AI Tutors in Math Mistake Remediation","created":"2026-03-25","cited_by_count":0,"area":"alignment"},{"id":"2604.04036","title":"MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.07583","title":"CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.12419","title":"GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.21502","title":"Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation","created":"2026-06-19","cited_by_count":0,"area":"alignment"},{"id":"2606.22349","title":"Curiosity as Linguistic Intervention: Using LLM Tutoring Dialogues to Influence Exploratory Learning Behavior","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.15692","title":"Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}