Beliefs and Misconceptions around Integrated Conversational AI

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Seymour, William, Jenkins, Adam, Cote, Mark, Such, Jose
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914567460749312
author Seymour, William
Jenkins, Adam
Cote, Mark
Such, Jose
author_facet Seymour, William
Jenkins, Adam
Cote, Mark
Such, Jose
contents LLM-driven conversational AI is beginning to disappear into the background, shifting from something used directly towards something increasingly integrated into existing workflows. In the process, markers of origin and training are smoothed away as LLMs become commodified in the eyes of users. We explore how people approach using a web browser with conversational AI built in, focusing on how they develop their understanding and determine whether to trust its outputs. We conducted a study where 20 participants used the Copilot AI features in Microsoft Edge to conduct information retrieval and planning tasks. Participants relied on a combination of existing perceptions of LLMs and internet search, tracing the effect of beliefs about how Copilot generated answers on prompting strategies. The inclusion of citations increased the trustworthiness of answers without participants feeling the need to be check them, with participants often reaching for the same information sources as the CAI when fact-checking.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14849
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beliefs and Misconceptions around Integrated Conversational AI
Seymour, William
Jenkins, Adam
Cote, Mark
Such, Jose
Human-Computer Interaction
LLM-driven conversational AI is beginning to disappear into the background, shifting from something used directly towards something increasingly integrated into existing workflows. In the process, markers of origin and training are smoothed away as LLMs become commodified in the eyes of users. We explore how people approach using a web browser with conversational AI built in, focusing on how they develop their understanding and determine whether to trust its outputs. We conducted a study where 20 participants used the Copilot AI features in Microsoft Edge to conduct information retrieval and planning tasks. Participants relied on a combination of existing perceptions of LLMs and internet search, tracing the effect of beliefs about how Copilot generated answers on prompting strategies. The inclusion of citations increased the trustworthiness of answers without participants feeling the need to be check them, with participants often reaching for the same information sources as the CAI when fact-checking.
title Beliefs and Misconceptions around Integrated Conversational AI
topic Human-Computer Interaction
url https://arxiv.org/abs/2605.14849