How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914017165967360 |
|---|---|
| author | Li, Ruijia Jiang, Yuan-Hao Wang, Jiatong Jiang, Bo |
| author_facet | Li, Ruijia Jiang, Yuan-Hao Wang, Jiatong Jiang, Bo |
| contents | Heuristic and scaffolded teacher-student dialogues are widely regarded as critical for fostering students' higher-order thinking and deep learning. However, large language models (LLMs) currently face challenges in generating pedagogically rich interactions. This study systematically investigates the structural and behavioral differences between AI-simulated and authentic human tutoring dialogues. We conducted a quantitative comparison using an Initiation-Response-Feedback (IRF) coding scheme and Epistemic Network Analysis (ENA). The results show that human dialogues are significantly superior to their AI counterparts in utterance length, as well as in questioning (I-Q) and general feedback (F-F) behaviors. More importantly, ENA results reveal a fundamental divergence in interactional patterns: human dialogues are more cognitively guided and diverse, centered around a "question-factual response-feedback" teaching loop that clearly reflects pedagogical guidance and student-driven thinking; in contrast, simulated dialogues exhibit a pattern of structural simplification and behavioral convergence, revolving around an "explanation-simplistic response" loop that is essentially a simple information transfer between the teacher and student. These findings illuminate key limitations in current AI-generated tutoring and provide empirical guidance for designing and evaluating more pedagogically effective generative educational dialogue systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01914 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction Li, Ruijia Jiang, Yuan-Hao Wang, Jiatong Jiang, Bo Artificial Intelligence Computation and Language Multiagent Systems Heuristic and scaffolded teacher-student dialogues are widely regarded as critical for fostering students' higher-order thinking and deep learning. However, large language models (LLMs) currently face challenges in generating pedagogically rich interactions. This study systematically investigates the structural and behavioral differences between AI-simulated and authentic human tutoring dialogues. We conducted a quantitative comparison using an Initiation-Response-Feedback (IRF) coding scheme and Epistemic Network Analysis (ENA). The results show that human dialogues are significantly superior to their AI counterparts in utterance length, as well as in questioning (I-Q) and general feedback (F-F) behaviors. More importantly, ENA results reveal a fundamental divergence in interactional patterns: human dialogues are more cognitively guided and diverse, centered around a "question-factual response-feedback" teaching loop that clearly reflects pedagogical guidance and student-driven thinking; in contrast, simulated dialogues exhibit a pattern of structural simplification and behavioral convergence, revolving around an "explanation-simplistic response" loop that is essentially a simple information transfer between the teacher and student. These findings illuminate key limitations in current AI-generated tutoring and provide empirical guidance for designing and evaluating more pedagogically effective generative educational dialogue systems. |
| title | How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction |
| topic | Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2509.01914 |