To err is AI

Alba Bisante, Alan Dix, Emanuele Panizzi, Stefano Zeppieri

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

1 Citation (Scopus)

Abstract

In this work, we analyze the different contexts in which one chooses to integrate artificial intelligence into an interface and the implications of this choice in managing user interaction. While AI in systems can provide significant benefits, it is not infallible and can make errors that seriously affect users. We aim to understand how to design more robust human-AI systems so that these initial AI errors do not lead to more catastrophic failures. To prevent failures, it is essential to detect errors as early as possible and have clear mechanisms to repair them. However, detecting errors in AI systems can be challenging. Therefore, we examine various approaches to error detection and repair, including post-hoc estimation, the use of traces and ambiguity, and multiple sensor layers.

Original languageEnglish
Title of host publicationCHItaly 2023 - Crossing HCI and AI
Subtitle of host publicationProceedings of the 15th Biannual Conference of the Italian SIGCHI Chapter
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400708060
DOIs
Publication statusPublished - 20 Sept 2023
Event15th Biannual Conference of the Italian SIGCHI Chapter: Crossing HCI and AI, CHItaly 2023 - Hybrid, Torino, Italy
Duration: 20 Sept 202322 Sept 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference15th Biannual Conference of the Italian SIGCHI Chapter: Crossing HCI and AI, CHItaly 2023
Country/TerritoryItaly
CityHybrid, Torino
Period20/09/2322/09/23

Keywords

  • AI
  • HCI
  • error detection
  • error repair
  • errors
  • failures
  • interaction design
  • user perception

Cite this