Voice Assistants' Accountability through Explanatory Dialogues

Fatemeh Alizadeh, Peter Tolmie, Minha Lee, Philipp Wintersberger, Dominik Pins, Gunnar Stevens

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

As voice assistants (VAs) become more advanced leveraging Large Language Models (LLMs) and natural language processing, their potential for accountable behavior expands. Yet, the long-term situational effectiveness of VAs' accounts when errors occur remains unclear. In our 19-month exploratory study with 19 households, we investigated the impact of an Alexa feature that allows users to inquire about the reasons behind its actions. Our findings indicate that Alexa's accounts are often single, decontextualized responses that led to users' alternative repair strategies over the long term, such as turning off the device, rather than initiating a dialogue about what went wrong. Through role-playing workshops, we demonstrate that VA interactions should facilitate explanatory dialogues as dynamic exchanges that consider a range of speech acts, recognizing users' emotional states and the context of interaction. We conclude by discussing the implications of our findings for the design of accountable VAs.

Original languageEnglish
Title of host publicationProceedings of the 6th Conference on ACM Conversational User Interfaces, CUI 2024
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400705113
DOIs
Publication statusPublished - 8 Jul 2024
Event6th Conference on ACM Conversational User Interfaces, CUI 2024 - Luxembourg City, Luxembourg
Duration: 8 Jul 202410 Jul 2024

Publication series

NameProceedings of the 6th Conference on ACM Conversational User Interfaces, CUI 2024

Conference

Conference6th Conference on ACM Conversational User Interfaces, CUI 2024
Country/TerritoryLuxembourg
CityLuxembourg City
Period08.07.202410.07.2024

Fingerprint

Dive into the research topics of 'Voice Assistants' Accountability through Explanatory Dialogues'. Together they form a unique fingerprint.

Cite this