EUVIMEDEUVIMED entdecken
Crossref

Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots

Milena Belošević, Hendrik Buschmeier

Publikationen an der Universität Bielefeld (Universität Bielefeld) · 22.07.2024

DOI: 10.11576/dataninja-1160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Publikationen an der Universität Bielefeld (Universität Bielefeld), erschienen am 22.07.2024. Verfasst von Milena Belošević und 1 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a linguistic approach to trust in human conversations with LLM-based chatbots. Using the concept of trust calibration as a starting point, we aim to address the question of how to increase user AI literacy and prevent misuse of as well as overtrust in the information provided by LLM-based chatbots in educational contexts. We propose a linguistic-based model of trust calibration that supports users in adopting a critical perspective on trust calibration and controlling their trust level. The method combines previous studies on trust in human interaction, specifically linguistic trust cues displayed by human trustors to indicate their level of trustworthiness in naturally occurring contexts with studies on proactive human-computer interaction and the social influence of conversational agent's embodiment in educational contexts.

Schlagwörter

trust calibrationLLM-based chatbotsAI literacyovertrustchatbotssocial influenceeducational technologyproactive interaction

Zitieren

APA

Belošević, M., & Buschmeier, H. (2024). Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. Publikationen an der Universität Bielefeld (Universität Bielefeld). https://doi.org/10.11576/dataninja-1160

Vancouver

Belošević M, Buschmeier H. Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. Publikationen an der Universität Bielefeld (Universität Bielefeld). 2024. doi:10.11576/dataninja-1160

BibTeX
@article{Beloevi2024,
  author = {Belošević, Milena and Buschmeier, Hendrik},
  title = {Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots},
  journal = {Publikationen an der Universität Bielefeld (Universität Bielefeld)},
  year = {2024},
  doi = {10.11576/dataninja-1160}
}
Kostenlos starten →