Skip to content

Evaluating the Usability of an LLM-Aided Hybrid Avatar Agent System

LLM 기반 하이브리드 아바타 에이전트 시스템의 사용성 평가

Document Type
Publications · Journal Article
Registered DB
KCI
Journal Ranking
KCI Q1
Journal
멀티미디어학회논문지26(8) · pp.874 · 2023
Citation
KCI 2
ISSN
1229-7771

Authors

  1. Junyeong, KumFirst author
  2. Taeyeon, Kim부산대학교 컴퓨터공학과
  3. Lee, MyunghoCorresponding author부산대학교

Abstract

The demand for conversational systems using digital humans has increased across various fields, including education and psychological counseling. Conversational digital humans can be categorized into avatar and agent. This paper introduces the Hybrid Avatar Agent System (HAAS), designed to implement a conversational digital human capable of addressing diverse questions. To facilitate seamless transitions between avatars and agents, we developed a Korean Dialogue Breakdown Detection (DBD) model. While a digital human typically functions as an agent, the DBD model identifies conversational pauses, prompting human operator intervention for user assistance. We trained DBD model using the RoBERTa_base model, achieving an accuracy of 60.77%. In a user study, a comparison was drawn between HAAS and the Agent Only System (AOS). Users noted that HAAS provided more appropriate answers than AOS.

Keywords

Dialogue Breakdown Detection ModelEmbodied Conversational AgentVirtual Human

Identifiers

KCI
ART002993381