{"total":95,"rows":[{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"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":"2310.10648","title":"Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes","created":"2023-10-16","cited_by_count":52,"area":null},{"id":"2404.12670","title":"Towards Human-centered Proactive Conversational Agents","created":"2024-04-19","cited_by_count":49,"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":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"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":"2404.06711","title":"MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education","created":"2024-04-10","cited_by_count":37,"area":null},{"id":"2309.01686","title":"MathAttack: Attacking Large Language Models Towards Math Solving Ability","created":"2023-09-04","cited_by_count":32,"area":null},{"id":"2402.09216","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","created":"2024-02-14","cited_by_count":31,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"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":"2401.18070","title":"Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?","created":"2024-01-31","cited_by_count":19,"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":"2402.11111","title":"Language Models as Science Tutors","created":"2024-02-16","cited_by_count":17,"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":"2407.03974","title":"LLM Roleplay: Simulating Human-Chatbot Interaction","created":"2024-07-04","cited_by_count":15,"area":null},{"id":"2404.06762","title":"Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems","created":"2024-04-10","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":"2503.07928","title":"The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2510.05087","title":"TeachLM: Post-Training LLMs for Education Using Authentic Learning Data","created":"2025-10-06","cited_by_count":9,"area":null},{"id":"2410.11123","title":"A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education","created":"2024-10-14","cited_by_count":8,"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":"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":"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":"2404.04728","title":"Navigating the Landscape of Hint Generation Research: From the Past to the Future","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2507.12484","title":"AI-Powered Math Tutoring: Platform for Personalized and Adaptive Education","created":"2025-07-14","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":"2410.19231","title":"Developing a Tutoring Dialog Dataset to Optimize LLMs for Educational Use","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2502.05651","title":"KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy","created":"2025-02-08","cited_by_count":5,"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":"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":"2601.08402","title":"PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.15531","title":"EduEVAL-DB: A Role-Based Dataset for Pedagogical Risk Evaluation in Educational Explanations","created":"2026-02-17","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":"2507.08232","title":"Can LLMs Reliably Simulate Real Students' Abilities in Mathematics and Reading Comprehension?","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.05283","title":"Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2603.17373","title":"SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2605.30051","title":"Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2607.01934","title":"AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations","created":"2026-07-02","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":"2506.02412","title":"SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2601.04219","title":"AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2603.02775","title":"From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2605.01097","title":"Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2606.16206","title":"Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2412.13395","title":"Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse","created":"2024-12-18","cited_by_count":1,"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":"2506.01524","title":"V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat","created":"2025-06-02","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":"2508.04563","title":"SID: Benchmarking Guided Instruction Capabilities in STEM Education with a Socratic Interdisciplinary Dialogues Dataset","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.08715","title":"MultiGen: Child-Friendly Multilingual Speech Generator with LLMs","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.19993","title":"MathBuddy: A Multimodal System for Affective Math Tutoring","created":"2025-08-27","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":"2512.03688","title":"AITutor-EvalKit: Exploring the Capabilities of AI Tutors","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.08950","title":"ConvoLearn: A Learning Sciences Grounded Dataset for Fine-Tuning Dialogic AI Tutors","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2602.16820","title":"AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2606.15766","title":"Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deployments","created":"2026-06-14","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":"2405.12100","title":"DOP: Diagnostic-Oriented Prompting for Large Language Models in Mathematical Correction","created":"2024-05-20","cited_by_count":0,"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":"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":"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":"2605.12748","title":"Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.14322","title":"Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.27088","title":"LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.30673","title":"TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.01020","title":"Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.06546","title":"Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios","created":"2026-06-04","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":"2606.21557","title":"PeerMathDial: A Middle School Dialogue Dataset for Student Collaborative Math Problem Solving","created":"2026-06-19","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":"2607.21306","title":"AI Assistants Overassist","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.22996","title":"Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning","created":"2026-07-25","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":"2608.00515","title":"Auditable Release Control for Pedagogical Leakage in LLM Tutors","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.09548","title":"ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models","created":"2026-08-10","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":"2609.12331","title":"Simulating Disengaged Students to Evaluate LLM-based Tutors","created":"2026-09-11","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},{"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":"2609.28026","title":"Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing","created":"2026-09-23","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":"2609.38359","title":"Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks","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},{"id":"2610.19532","title":"A Unified Response Framework for Questions and Tutoring Dialogues","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}