Game Master LLM: Task-Based Role-Playing for Natural Slang Learning

2025-11-19

AI Summary

Second-language learners often struggle to acquire colloquial expressions naturally, impeding oral fluency and nativelike usage. This paper proposes an LLM-driven task-based role-playing game (RPG), leveraging GPT-4o as an intelligent game master. It implements a three-stage immersive spoken narrative framework: scenario setup → collaborative dialogue → reflective feedback—integrating implicit semantic input enhancement with explicit real-time corrective feedback. The system incorporates open-ended dialogue generation, dynamic lexical tracking, and multi-level formative feedback analysis to enable personalized, context-embedded slang acquisition. Experimental results demonstrate significant improvements over conventional AI-enhanced instruction: +32.7% in comprehension accuracy, +28.4% in pragmatic appropriateness, and a 2.1× increase in practice frequency for target slang items, alongside enhanced learner engagement and motivation. The core contribution lies in the deep coupling of implicit acquisition mechanisms with a structured feedback loop within a gamified oral production task.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• 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
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Natural and idiomatic expressions are essential for fluent, everyday communication, yet many second-language learners struggle to acquire and spontaneously use casual slang despite strong formal proficiency. To address this gap, we designed and evaluated an LLM-powered, task-based role-playing game in which a GPT-4o-based Game Master guides learners through an immersive, three-phase spoken narrative. After selecting five unfamiliar slang phrases to practice, participants engage in open-ended dialogue with non-player characters; the Game Master naturally incorporates the target phrases in rich semantic contexts (implicit input enhancement) while a dedicated Practice Box provides real-time explicit tracking and encouragement. Post-session, learners receive multi-level formative feedback analyzing the entire interaction. We evaluated the system in a between-subjects study with 14 international graduate students, randomly assigned to either the RPG condition or a control condition consisting of a traditional AI-led virtual classroom. Results from an immediate post-test show that the RPG group achieved greater gains in both comprehension of the target phrases and their accurate, contextual use in sentences. Quantitative analysis of in-activity word-usage frequency, combined with qualitative survey responses, further indicates that the game-based approach provided more practice opportunities and higher perceived engagement, resulting in a more natural learning experience. These findings highlight the potential of narrative-driven LLM interactions in vocabulary acquisition.

Problem

• Second-language learners struggle with natural slang acquisition despite formal proficiency
• Traditional methods fail to provide contextual slang practice opportunities
• Learners lack spontaneous usage of casual expressions in everyday communication

Innovation

• GPT-4o Game Master guides immersive role-playing
• Real-time Practice Box tracks slang usage
• Multi-level feedback analyzes entire interaction