ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VR

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Mengxu, Kitson, Alexandra, Wan, Hongyu, Prpa, Mirjana
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912056765054976
author Pan, Mengxu
Kitson, Alexandra
Wan, Hongyu
Prpa, Mirjana
author_facet Pan, Mengxu
Kitson, Alexandra
Wan, Hongyu
Prpa, Mirjana
contents Many people struggle with learning a new language, with traditional tools falling short in providing contextualized learning tailored to each learner's needs. The recent development of large language models (LLMs) and embodied conversational agents (ECAs) in social virtual reality (VR) provide new opportunities to practice language learning in a contextualized and naturalistic way that takes into account the learner's language level and needs. To explore this opportunity, we developed ELLMA-T, an ECA that leverages an LLM (GPT-4) and situated learning framework for supporting learning English language in social VR (VRChat). Drawing on qualitative interviews (N=12), we reveal the potential of ELLMA-T to generate realistic, believable and context-specific role plays for agent-learner interaction in VR, and LLM's capability to provide initial language assessment and continuous feedback to learners. We provide five design implications for the future development of LLM-based language agents in social VR.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02406
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VR
Pan, Mengxu
Kitson, Alexandra
Wan, Hongyu
Prpa, Mirjana
Human-Computer Interaction
Many people struggle with learning a new language, with traditional tools falling short in providing contextualized learning tailored to each learner's needs. The recent development of large language models (LLMs) and embodied conversational agents (ECAs) in social virtual reality (VR) provide new opportunities to practice language learning in a contextualized and naturalistic way that takes into account the learner's language level and needs. To explore this opportunity, we developed ELLMA-T, an ECA that leverages an LLM (GPT-4) and situated learning framework for supporting learning English language in social VR (VRChat). Drawing on qualitative interviews (N=12), we reveal the potential of ELLMA-T to generate realistic, believable and context-specific role plays for agent-learner interaction in VR, and LLM's capability to provide initial language assessment and continuous feedback to learners. We provide five design implications for the future development of LLM-based language agents in social VR.
title ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VR
topic Human-Computer Interaction
url https://arxiv.org/abs/2410.02406