Reproduce “GenQuest: An LLM-based Text Adventure Game for Language Learners” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Qiao Wang, Adnan Labib, Robert Swier, Michael Hofmeyr, Zheng Yuan
Researchers developed GenQuest, an LLM-powered text adventure game designed to enhance second language learning through dynamic, personalized narratives and in-context language support. A pilot study showed participants achieved an average vocabulary acquisition score of 13.44 out of 20 for queried words, alongside strong positive user perceptions of the system's usefulness and ease of use.
Key insights
- LLMs can effectively generate dynamic, personalized narratives and adapt linguistic complexity, addressing the limitations of static content in traditional language learning games.
- Providing in-context explanations and vocabulary tracking within an interactive game environment supports incidental vocabulary acquisition and enhances reading comprehension for language learners.
- User feedback highlights key areas for future development in LLM-powered educational tools, such as the need for more granular difficulty adjustment, multimodal content integration, and improved narrative consistency.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.