Child-Centric Robot Dialogue Systems: Fine-Tuning Large Language Models for Better Utterance Understanding and Interaction
Sensors · 12.12.2024 · 24 (24) · 7939
DOI: 10.3390/s24247939 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.12.2024. Verfasst von Da-Young Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Human-Robot Interaction Center, Korea Institute of Robotics & Technology Convergence (KIRO), Pohang 37553, Republic of Korea. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education and the National Research Foundation of Korea, Institute for Information & Communications Technology Planning & Evaluation, MSIT (Ministry of Science and ICT), Korea.
Abstract (Originalsprache)
Dialogue systems must understand children’s utterance intentions by considering their unique linguistic characteristics, such as syntactic incompleteness, pronunciation inaccuracies, and creative expressions, to enable natural conversational engagement in child–robot interactions. Even state-of-the-art large language models (LLMs) for language understanding and contextual awareness cannot comprehend children’s intent as accurately as humans because of their distinctive features. An LLM-based dialogue system should acquire the manner by which humans understand children’s speech to enhance its intention reasoning performance in verbal interactions with children. To this end, we propose a fine-tuning methodology that utilizes the LLM–human judgment discrepancy and interactive response data. The former data represent cases in which the LLM and human judgments of the contextual appropriateness of a child’s answer to a robot’s question diverge. The latter data involve robot responses suitable for children’s utterance intentions, generated by the LLM. We developed a fine-tuned dialogue system using these datasets to achieve human-like interpretations of children’s utterances and to respond adaptively. Our system was evaluated through human assessment using the Robotic Social Attributes Scale (RoSAS) and Sensibleness and Specificity Average (SSA) metrics. Consequently, it supports the effective interpretation of children’s utterance intentions and enables natural verbal interactions, even in cases with syntactic incompleteness and mispronunciations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Human-Robot Interaction Center, Korea Institute of Robotics & Technology Convergence (KIRO), Pohang 37553, Republic of Korea.
- Department of Information Convergence Engineering, Pusan National University, Busan 46241, Republic of Korea.
ORCID-Profile: Da-Young Kim, Hyo Jeong Lym, Hanna Lee, Ye Jun Lee, Juhyun Kim, Min-Gyu Kim
Förderung
- Ministry of Education and the National Research Foundation of Korea
- Institute for Information & Communications Technology Planning & Evaluation
- MSIT (Ministry of Science and ICT), Korea
- IITP (Institute for Information & Communications Technology Planning & Evaluation)
Zitieren
APA
Kim, D. Y., Lym, H. J., Lee, H., Lee, Y. J., Kim, J., Kim, M. G., & Baek, Y. (2024). Child-Centric Robot Dialogue Systems: Fine-Tuning Large Language Models for Better Utterance Understanding and Interaction. Sensors, 24(24), 7939. https://doi.org/10.3390/s24247939
Vancouver
Kim DY, Lym HJ, Lee H, Lee YJ, Kim J, Kim MG, et al. Child-Centric Robot Dialogue Systems: Fine-Tuning Large Language Models for Better Utterance Understanding and Interaction. Sensors. 2024;24(24):7939. doi:10.3390/s24247939
BibTeX
@article{Kim2024,
author = {Kim, Da-Young and Lym, Hyo Jeong and Lee, Hanna and Lee, Ye Jun and Kim, Juhyun and Kim, Min-Gyu and Baek, Yunju},
title = {Child-Centric Robot Dialogue Systems: Fine-Tuning Large Language Models for Better Utterance Understanding and Interaction},
journal = {Sensors},
year = {2024},
volume = {24},
number = {24},
pages = {7939},
doi = {10.3390/s24247939}
}
EUVIMED