{"total":30,"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":"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":"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":"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":"2601.04025","title":"Simulated Students in Tutoring Dialogues: Substance or Illusion?","created":"2026-01-07","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":"2502.15140","title":"Do LLMs Make Mistakes Like Students? Exploring Natural Alignment between Language Models and Human Error Patterns","created":"2025-02-21","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":"2509.01395","title":"LLMs cannot spot math errors, even when allowed to peek into the solution","created":"2025-09-01","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":"2507.22753","title":"Opportunities and Challenges of LLMs in Education: An NLP Perspective","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2412.16838","title":"Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions","created":"2024-12-22","cited_by_count":4,"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":"2506.04920","title":"Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2505.18056","title":"MathEDU: Feedback Generation on Problem-Solving Processes for Mathematical Learning Support","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2505.04736","title":"The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems","created":"2025-05-07","cited_by_count":1,"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":"2606.30578","title":"Uncertainty-Aware Generation and Decision-Making Under Ambiguity","created":"2026-06-29","cited_by_count":1,"area":null},{"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":"2603.25633","title":"Is Mathematical Problem-Solving Expertise in Large Language Models Associated with Assessment Performance?","created":"2026-03-26","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":"2606.18257","title":"From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions","created":"2026-05-06","cited_by_count":0,"area":null},{"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":"2606.23205","title":"The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.21306","title":"AI Assistants Overassist","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.27309","title":"Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.22553","title":"Correct Diagnosis, Better Feedback: A Symbolic-Verifier for Faithful LLM Tutoring Feedback in Logic Proofs","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.38346","title":"Examining Variation in How Guided AI Tutors Resolve Student Impasses","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04825","title":"DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring","created":"2026-10-04","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}