The field of explainable artificial intelligence (XAI) is gaining increasing importance in recent years. As a consequence, several surveys have been published to explore the current state of the art on this topic. One aspect that seems to be overlooked by these works is the applied presentation methods and, specifically, the role of natural language in generating the final explanations. This survey reviews 70 XAI papers published between 2006 and 2021 and evaluates their readiness with respect to natural language explanations. Thus, together with a set of hierarchical criteria, we define a multi-criteria decision-making model. Finally, we conclude that only a handful of recent XAI works either considered natural language explanations to approach final users (see, e.g.,(Bennetot et al., 2021)) or implemented a method capable of generating such explanations.

Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N. (2023). A survey on XAI and natural language explanations. INFORMATION PROCESSING & MANAGEMENT, 60(1) [10.1016/j.ipm.2022.103111].

A survey on XAI and natural language explanations

Malandri L.
;
Mercorio F.
;
Mezzanzanica M.
;
Nobani N.
2023

Abstract

The field of explainable artificial intelligence (XAI) is gaining increasing importance in recent years. As a consequence, several surveys have been published to explore the current state of the art on this topic. One aspect that seems to be overlooked by these works is the applied presentation methods and, specifically, the role of natural language in generating the final explanations. This survey reviews 70 XAI papers published between 2006 and 2021 and evaluates their readiness with respect to natural language explanations. Thus, together with a set of hierarchical criteria, we define a multi-criteria decision-making model. Finally, we conclude that only a handful of recent XAI works either considered natural language explanations to approach final users (see, e.g.,(Bennetot et al., 2021)) or implemented a method capable of generating such explanations.
Articolo in rivista - Articolo scientifico
Explainable AI; Natural language explanations; Presentation methods;
English
25-ott-2022
2023
60
1
103111
reserved
Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N. (2023). A survey on XAI and natural language explanations. INFORMATION PROCESSING & MANAGEMENT, 60(1) [10.1016/j.ipm.2022.103111].
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0306457322002126-main.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 2.44 MB
Formato Adobe PDF
2.44 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10281/396173
Citazioni
  • Scopus 91
  • ???jsp.display-item.citation.isi??? 62
Social impact