Guardado en:
Detalles Bibliográficos
Autores principales: Tahmasbi, Amir, Esrafilian, Milad, Wright, Judson, Jeong, Sooyeon, Bera, Aniket
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.15504
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911579276050432
author Tahmasbi, Amir
Esrafilian, Milad
Wright, Judson
Jeong, Sooyeon
Bera, Aniket
author_facet Tahmasbi, Amir
Esrafilian, Milad
Wright, Judson
Jeong, Sooyeon
Bera, Aniket
contents 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. A one-week delayed post-test further demonstrates that these gains are retained over time, with the RPG group showing a 21-27% improvement, indicating the effectiveness of our approach in supporting longer-term learning. Qualitative survey responses assessing engagement and perceived effectiveness further indicate that the game-based approach provided more practice opportunities and a more natural learning experience. These findings highlight the potential of narrative-driven LLM interactions in vocabulary acquisition.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15504
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Game Master LLM: Task-Based Role-Playing for Natural Slang Learning
Tahmasbi, Amir
Esrafilian, Milad
Wright, Judson
Jeong, Sooyeon
Bera, Aniket
Human-Computer Interaction
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. A one-week delayed post-test further demonstrates that these gains are retained over time, with the RPG group showing a 21-27% improvement, indicating the effectiveness of our approach in supporting longer-term learning. Qualitative survey responses assessing engagement and perceived effectiveness further indicate that the game-based approach provided more practice opportunities and a more natural learning experience. These findings highlight the potential of narrative-driven LLM interactions in vocabulary acquisition.
title Game Master LLM: Task-Based Role-Playing for Natural Slang Learning
topic Human-Computer Interaction
url https://arxiv.org/abs/2511.15504