GenQuest: An LLM-based Text Adventure Game for Language Learners

TL;DR

GenQuest investigates LLM-powered branching narratives as a personalized tool for second language learning. The system combines Claude 3.7 for coherent plot generation with GPT-4o for in-context vocabulary explanations, pairing a memory-informed story module with a language scaffolding module. A five-day pilot with nine Chinese EFL undergraduates shows vocabulary gains and generally positive perceptions, while also revealing areas for improvement in narrative coherence, difficulty calibration, and multimodal engagement. The work presents a scalable framework for adaptive, narrative-based language learning and suggests clear directions for broader deployment and longer-term evaluation.

Abstract

GenQuest is a generative text adventure game that leverages Large Language Models (LLMs) to facilitate second language learning through immersive, interactive storytelling. The system engages English as a Foreign Language (EFL) learners in a collaborative "choose-your-own-adventure" style narrative, dynamically generated in response to learner choices. Game mechanics such as branching decision points and story milestones are incorporated to maintain narrative coherence while allowing learner-driven plot development. Key pedagogical features include content generation tailored to each learner's proficiency level, and a vocabulary assistant that provides in-context explanations of learner-queried text strings, ranging from words and phrases to sentences. Findings from a pilot study with university EFL students in China indicate promising vocabulary gains and positive user perceptions. Also discussed are suggestions from participants regarding the narrative length and quality, and the request for multi-modal content such as illustrations.

Figures (4)

• Figure 1: Architecture and workflow of the story module
• Figure 2: User input at game initiation
• Figure 3: Example texts for six CEFR levels.
• Figure 4: Language query and query history