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

Belosevic M, Buschmeier H (2024)
In: Proceedings of the DataNinja sAIOnARA 2024 Conference. Kuhl U (Ed); Bielefeld: BieColl.

Kurzbeitrag Konferenz / Poster | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Herausgeber*in
Kuhl, Ulrike
Abstract / Bemerkung
This paper presents a linguistic approach to trust in human conversations with LLM-based chatbots. Using the concept of trust calibration [Muir 1987] 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 (see Nielsen and Nielsen 2022) with studies on proactive human-computer interaction (Kraus et al. 2021) and the social influence of conversational agent's embodiment in educational contexts (Leyzberg et al. 2012).
Stichworte
dililab
Erscheinungsjahr
2024
Titel des Konferenzbandes
Proceedings of the DataNinja sAIOnARA 2024 Conference
Konferenz
DataNinja sAIOnARA 2024 Conference
Konferenzort
Bielefeld, Germany
Konferenzdatum
2024-06-25 – 2024-06-27
Page URI
https://pub.uni-bielefeld.de/record/2993531

Zitieren

Belosevic M, Buschmeier H. Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. In: Kuhl U, ed. Proceedings of the DataNinja sAIOnARA 2024 Conference. Bielefeld: BieColl; 2024.
Belosevic, M., & Buschmeier, H. (2024). Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. In U. Kuhl (Ed.), Proceedings of the DataNinja sAIOnARA 2024 Conference Bielefeld: BieColl. https://doi.org/10.11576/dataninja-1160
Belosevic, Milena, and Buschmeier, Hendrik. 2024. “Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots”. In Proceedings of the DataNinja sAIOnARA 2024 Conference, ed. Ulrike Kuhl. Bielefeld: BieColl.
Belosevic, M., and Buschmeier, H. (2024). “Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots” in Proceedings of the DataNinja sAIOnARA 2024 Conference, Kuhl, U. ed. (Bielefeld: BieColl).
Belosevic, M., & Buschmeier, H., 2024. Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. In U. Kuhl, ed. Proceedings of the DataNinja sAIOnARA 2024 Conference. Bielefeld: BieColl.
M. Belosevic and H. Buschmeier, “Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots”, Proceedings of the DataNinja sAIOnARA 2024 Conference, U. Kuhl, ed., Bielefeld: BieColl, 2024.
Belosevic, M., Buschmeier, H.: Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots. In: Kuhl, U. (ed.) Proceedings of the DataNinja sAIOnARA 2024 Conference. BieColl, Bielefeld (2024).
Belosevic, Milena, and Buschmeier, Hendrik. “Linguistic-Based Reflection on Trust Calibration in Conversations with LLM-Based Chatbots”. Proceedings of the DataNinja sAIOnARA 2024 Conference. Ed. Ulrike Kuhl. Bielefeld: BieColl, 2024.
Externes Material:
Zusatzmaterial
Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar