Artykuł w czasopiśmie
Brak miniatury
Licencja
ClosedAccessDostęp zamknięty
 

Explainable artificial intelligence, lawyer's perspective

Uproszczony widok
dc.abstract.enExplainable artificial intelligence (XAI) is a research direction that was already put under scrutiny, in particular in the AI&Law community. Whilst there were notable developments in the area of (general, not necessarily legal) XAI, user experience studies regarding such methods, as well as more general studies pertaining to the concept of explainability among the users are still lagging behind. This paper firstly, assesses the performance of different explainability methods (Grad-CAM, LIME, SHAP), in explaining the predictions for a legal text classification problem; those explanations were then judged by legal professionals according to their accuracy. Secondly, the same respondents were asked to give their opinion on the desired qualities of (explainable) artificial intelligence (AI) legal decision system and to present their general understanding of the term XAI. This part was treated as a pilot study for a more pronounced one regarding the lawyer's position on AI, and XAI in particular.
dc.affiliationUniwersytet Warszawski
dc.conference.countryBrazylia
dc.conference.datefinish2021-06-25
dc.conference.datestart2021-06-21
dc.conference.placevirtual
dc.conference.seriesInternational Conference on Artificial Intelligence and Law
dc.conference.seriesInternational Conference on Artificial Intelligence and Law
dc.conference.seriesshortcutICAIL
dc.conference.shortcutICAIL 2021
dc.conference.weblinkhttps://icail.lawgorithm.com.br/
dc.contributor.authorGórski, Łukasz
dc.contributor.authorRamakrishna, Shashishekar
dc.date.accessioned2024-01-25T00:09:49Z
dc.date.available2024-01-25T00:09:49Z
dc.date.issued2021
dc.description.financePublikacja bezkosztowa
dc.identifier.doi10.1145/3462757.3466145
dc.identifier.urihttps://repozytorium.uw.edu.pl//handle/item/106784
dc.identifier.weblinkhttps://dl.acm.org/doi/pdf/10.1145/3462757.3466145
dc.languageeng
dc.pbn.affiliationcomputer and information sciences
dc.relation.pages60–68
dc.rightsClosedAccess
dc.sciencecloudnosend
dc.titleExplainable artificial intelligence, lawyer's perspective
dc.typeJournalArticle
dspace.entity.typePublication