How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction

2025-09-01

AI Summary

Current large language models (LLMs) exhibit structural deficiencies in simulating one-on-one pedagogical dialogue: whereas human teachers enact a cognitively guided “Initiation–Response–Feedback” (IRF) cycle, LLMs predominantly default to unidirectional “explanation–simple response” information transmission. Method: We conduct a quantitative comparative analysis of authentic human teaching dialogues and LLM-generated dialogues using IRF discourse coding and Epistemic Network Analysis (ENA), measuring turn complexity, frequency of higher-order questions, and feedback depth. Contribution/Results: Human dialogues significantly outperform AI-generated ones across all three dimensions. This study is the first to systematically identify the core limitation of generative educational systems—namely, their inability to provide dynamic cognitive scaffolding—thereby impeding higher-order thinking development. It provides empirical grounding and actionable design principles for next-generation pedagogically sensitive educational dialogue systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• Comparing AI-simulated and human tutoring dialogues structurally
• Investigating pedagogical limitations in AI-generated educational interactions
• Identifying behavioral divergence in cognitive guidance patterns

Innovation

• Initiation-Response-Feedback coding scheme
• Epistemic Network Analysis methodology
• Comparative analysis human-AI dialogue patterns