Game Master LLM: Task-Based Role-Playing for Natural Slang Learning
Amir Tahmasbi, Milad Esrafilian, Judson Wright, Sooyeon Jeong, Aniket Bera

TL;DR
This paper presents an LLM-powered role-playing game that improves learners' understanding and use of casual slang through immersive, task-based interactions, showing significant short-term and long-term learning gains.
Contribution
It introduces a novel, immersive, role-playing approach using GPT-4o to enhance slang learning, with evidence of improved retention and engagement compared to traditional methods.
Findings
RPG group showed greater immediate gains in slang comprehension and usage.
One-week delayed post-test indicated 21-27% retention improvement.
Qualitative feedback favored game-based learning for engagement and natural practice.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
