In this paper we focus on the importance of interpreting the quality of the input of predictive models (potentially a GI, i.e., a Garbage In) to make sense of the reliability of their output (potentially a GO, a Garbage Out) in support of human decision making, especially in critical domains, like medicine. To this aim, we propose a framework where we distinguish between the Gold Standard (or Ground Truth) and the set of annotations from which this is derived, and a set of quality dimensions that help to assess and interpret the AI advice: fineness, trueness, representativeness, conformity, dryness. We then discuss implications for obtaining more informative training sets and for the design of more usable Decision Support Systems.

Cabitza, F., Campagner, A., Ciucci, D. (2019). New Frontiers in Explainable AI: Understanding the GI to Interpret the GO. In Machine Learning and Knowledge Extraction Third IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2019, Canterbury, UK, August 26–29, 2019, Proceedings (pp.27-47). Springer Verlag [10.1007/978-3-030-29726-8_3].

New Frontiers in Explainable AI: Understanding the GI to Interpret the GO

Cabitza F.
;
Campagner A.;Ciucci D.
2019

Abstract

In this paper we focus on the importance of interpreting the quality of the input of predictive models (potentially a GI, i.e., a Garbage In) to make sense of the reliability of their output (potentially a GO, a Garbage Out) in support of human decision making, especially in critical domains, like medicine. To this aim, we propose a framework where we distinguish between the Gold Standard (or Ground Truth) and the set of annotations from which this is derived, and a set of quality dimensions that help to assess and interpret the AI advice: fineness, trueness, representativeness, conformity, dryness. We then discuss implications for obtaining more informative training sets and for the design of more usable Decision Support Systems.
paper
Explainable AI; Ground truth; Reliability; Usable AI;
English
Third IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2019 - August 26–29, 2019
2019
Machine Learning and Knowledge Extraction Third IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2019, Canterbury, UK, August 26–29, 2019, Proceedings
9783030297251
2019
11713
27
47
none
Cabitza, F., Campagner, A., Ciucci, D. (2019). New Frontiers in Explainable AI: Understanding the GI to Interpret the GO. In Machine Learning and Knowledge Extraction Third IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2019, Canterbury, UK, August 26–29, 2019, Proceedings (pp.27-47). Springer Verlag [10.1007/978-3-030-29726-8_3].
File in 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/10281/265891
Citazioni
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 7
Social impact