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

TL;DR

ELLMA-T is an embodied conversational agent using GPT-4 in social VR to support personalized English language learning through realistic role plays and continuous feedback, enhancing contextualized language practice.

Contribution

This paper introduces ELLMA-T, a novel LLM-powered embodied agent in social VR that offers personalized, context-aware language learning experiences, a first in this domain.

Findings

ELLMA-T can generate realistic, context-specific role plays.

LLM provides effective initial language assessment.

The system offers continuous, personalized feedback.

Abstract

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.