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.

To err is AI / Bisante, Alba; Dix, Alan; Panizzi, Emanuele; Zeppieri, Stefano. - (2023), pp. 1-11. (Intervento presentato al convegno CHItaly 2023: 15th Biannual Conference of the Italian SIGCHI Chapter tenutosi a Torino; Italy) [10.1145/3605390.3605414].

To err is AI

Alba Bisante
Conceptualization
;
Alan Dix
Conceptualization
;
Emanuele Panizzi
Conceptualization
;
Stefano Zeppieri
Conceptualization
2023

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.
2023
CHItaly 2023: 15th Biannual Conference of the Italian SIGCHI Chapter
AI; error detection; error repair; errors; failures; HCI; interaction design; user perception; Repair; User interfaces; AI systems; Catastrophic failures; Detection and repairs; Error repair; Interaction design; Multiple sensors; Sensor layers; User interaction; User perceptions; Error detection
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
To err is AI / Bisante, Alba; Dix, Alan; Panizzi, Emanuele; Zeppieri, Stefano. - (2023), pp. 1-11. (Intervento presentato al convegno CHItaly 2023: 15th Biannual Conference of the Italian SIGCHI Chapter tenutosi a Torino; Italy) [10.1145/3605390.3605414].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1691663
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact