{"total":31,"rows":[{"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":"2506.18710","title":"Benchmarking the Pedagogical Knowledge of Large Language Models","created":"2025-06-23","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":"2505.21775","title":"DualSchool: How Reliable are LLMs for Optimization Education?","created":"2025-05-27","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":"2507.12674","title":"ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2510.23477","title":"MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2512.19903","title":"How well do Large Language Models Recognize Instructional Moves? Establishing Baselines for Foundation Models in Educational Discourse","created":"2025-12-22","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":"2504.00843","title":"Benchmarking Large Language Models for Diagnosing Students' Cognitive Skills from Handwritten Math Work","created":"2025-04-01","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":"2512.03688","title":"AITutor-EvalKit: Exploring the Capabilities of AI Tutors","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2605.05648","title":"The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness","created":"2026-05-07","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":"2608.18554","title":"CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks","created":"2026-08-19","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":"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":"2603.26679","title":"AI Meets Mathematics Education: A Case Study on Supporting an Instructor in a Large Mathematics Class with Context-Aware AI","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.03236","title":"BLADE: Better Language Answers through Dialogue and Explanations","created":"2026-01-31","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":"2608.00515","title":"Auditable Release Control for Pedagogical Leakage in LLM Tutors","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.11259","title":"Methodologies for Improving the Quality of AI Tutoring in K-12 Education","created":"2026-08-07","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":"2609.23088","title":"OmniEdu: Open Foundation Models for Learning and Teaching","created":"2026-09-19","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}