Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems

2024-04-10

Conference on Empirical Methods in Natural Language Processing

AI Summary

Current conversational Intelligent Tutoring Systems (ITS) suffer from coarse-grained student personality modeling, hindering personalized dialogue training and evaluation. Method: We propose a multidimensional student persona framework integrating cognitive (linguistic competence) and non-cognitive (personality traits) dimensions, grounded in personality psychology theory. Leveraging large language models (LLMs), we generate linguistically and personality-consistent student responses in language-learning scenarios. We further introduce a novel teacher–student dual-perspective validation mechanism to enable adaptive, multi-dimensional assessment of pedagogical interactions. Contribution/Results: Experiments demonstrate that state-of-the-art LLMs generate significantly differentiated student utterances aligned with persona specifications, effectively eliciting dynamic teacher scaffolding strategies and substantially improving dialogue adaptability and personalization. This work constitutes the first systematic realization of personality-driven student simulation coupled with dual-perspective verifiable evaluation, establishing a new paradigm for trustworthy ITS training and human–AI collaborative teaching.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Intelligent Tutoring Systems (ITSs) can provide personalized and self-paced learning experience. The emergence of large language models (LLMs) further enables better human-machine interaction, and facilitates the development of conversational ITSs in various disciplines such as math and language learning. In dialogic teaching, recognizing and adapting to individual characteristics can significantly enhance student engagement and learning efficiency. However, characterizing and simulating student’s persona remain challenging in training and evaluating conversational ITSs. In this work, we propose a framework to construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personality-aware student simulation in a language learning scenario. We further enhance the framework with multi-aspect validation, and conduct extensive analysis from both teacher and student perspectives. Our experimental results show that state-of-the-art LLMs can produce diverse student responses according to the given language ability and personality traits, and trigger teacher’s adaptive scaffolding strategies.

Problem

• Simulating diverse student personas for conversational tutoring systems
• Integrating cognitive and noncognitive traits in student profiles
• Enhancing adaptive teaching strategies through personality-aware simulations

Innovation

• Leveraging LLMs for personality-aware student simulation
• Integrating cognitive and noncognitive student profiles
• Multi-aspect validation enhancing simulation framework