Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161731903> ?p ?o ?g. }
- W3161731903 endingPage "103525" @default.
- W3161731903 startingPage "103525" @default.
- W3161731903 abstract "Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers for this growth include recent legislative changes and increased investments by industry and governments, along with increased concern from the general public. People are affected by autonomous decisions every day and the public need to understand the decision-making process to accept the outcomes. However, the vast majority of the applications of XAI/IML are focused on providing low-level `narrow' explanations of how an individual decision was reached based on a particular datum. While important, these explanations rarely provide insights into an agent's: beliefs and motivations; hypotheses of other (human, animal or AI) agents' intentions; interpretation of external cultural expectations; or, processes used to generate its own explanation. Yet all of these factors, we propose, are essential to providing the explanatory depth that people require to accept and trust the AI's decision-making. This paper aims to define levels of explanation and describe how they can be integrated to create a human-aligned conversational explanation system. In so doing, this paper will survey current approaches and discuss the integration of different technologies to achieve these levels with Broad eXplainable Artificial Intelligence (Broad-XAI), and thereby move towards high-level `strong' explanations." @default.
- W3161731903 created "2021-05-24" @default.
- W3161731903 creator A5004509229 @default.
- W3161731903 creator A5013402425 @default.
- W3161731903 creator A5032749222 @default.
- W3161731903 creator A5038741954 @default.
- W3161731903 creator A5044098673 @default.
- W3161731903 creator A5080095540 @default.
- W3161731903 date "2021-10-01" @default.
- W3161731903 modified "2023-10-18" @default.
- W3161731903 title "Levels of explainable artificial intelligence for human-aligned conversational explanations" @default.
- W3161731903 cites W1498412273 @default.
- W3161731903 cites W188378287 @default.
- W3161731903 cites W1936290004 @default.
- W3161731903 cites W1964704223 @default.
- W3161731903 cites W1965229241 @default.
- W3161731903 cites W1971771969 @default.
- W3161731903 cites W1976029488 @default.
- W3161731903 cites W1981243943 @default.
- W3161731903 cites W1983905888 @default.
- W3161731903 cites W1999294210 @default.
- W3161731903 cites W2000309883 @default.
- W3161731903 cites W2000917789 @default.
- W3161731903 cites W2010256389 @default.
- W3161731903 cites W2013587512 @default.
- W3161731903 cites W2017561954 @default.
- W3161731903 cites W2030721126 @default.
- W3161731903 cites W2034637247 @default.
- W3161731903 cites W2041029272 @default.
- W3161731903 cites W2045856089 @default.
- W3161731903 cites W2048737604 @default.
- W3161731903 cites W2050648804 @default.
- W3161731903 cites W2060482235 @default.
- W3161731903 cites W2063046703 @default.
- W3161731903 cites W2067122120 @default.
- W3161731903 cites W2069452667 @default.
- W3161731903 cites W2072376581 @default.
- W3161731903 cites W2087700841 @default.
- W3161731903 cites W2089208009 @default.
- W3161731903 cites W2096434649 @default.
- W3161731903 cites W2108616861 @default.
- W3161731903 cites W2113669408 @default.
- W3161731903 cites W2119368976 @default.
- W3161731903 cites W2124756613 @default.
- W3161731903 cites W2125896931 @default.
- W3161731903 cites W2129639577 @default.
- W3161731903 cites W2133901799 @default.
- W3161731903 cites W2138143941 @default.
- W3161731903 cites W2139188400 @default.
- W3161731903 cites W2143426471 @default.
- W3161731903 cites W2145467192 @default.
- W3161731903 cites W2154988829 @default.
- W3161731903 cites W2165734786 @default.
- W3161731903 cites W2210721416 @default.
- W3161731903 cites W2227771027 @default.
- W3161731903 cites W2257979135 @default.
- W3161731903 cites W2274499208 @default.
- W3161731903 cites W2321579809 @default.
- W3161731903 cites W2397253692 @default.
- W3161731903 cites W2474744587 @default.
- W3161731903 cites W2507581019 @default.
- W3161731903 cites W2561515991 @default.
- W3161731903 cites W2582626238 @default.
- W3161731903 cites W2595754429 @default.
- W3161731903 cites W2598079398 @default.
- W3161731903 cites W2604372349 @default.
- W3161731903 cites W2618694529 @default.
- W3161731903 cites W2625332229 @default.
- W3161731903 cites W2762221702 @default.
- W3161731903 cites W2799547155 @default.
- W3161731903 cites W2883171104 @default.
- W3161731903 cites W2884993598 @default.
- W3161731903 cites W2891503716 @default.
- W3161731903 cites W2894821115 @default.
- W3161731903 cites W2896348597 @default.
- W3161731903 cites W2913163749 @default.
- W3161731903 cites W2917819557 @default.
- W3161731903 cites W2944782230 @default.
- W3161731903 cites W2945459164 @default.
- W3161731903 cites W2963143014 @default.
- W3161731903 cites W2963218601 @default.
- W3161731903 cites W2990540492 @default.
- W3161731903 cites W3021067255 @default.
- W3161731903 cites W3098163860 @default.
- W3161731903 cites W3122240369 @default.
- W3161731903 cites W3122497069 @default.
- W3161731903 cites W3126403556 @default.
- W3161731903 cites W3165003809 @default.
- W3161731903 cites W3189888336 @default.
- W3161731903 cites W4256654935 @default.
- W3161731903 doi "https://doi.org/10.1016/j.artint.2021.103525" @default.
- W3161731903 hasPublicationYear "2021" @default.
- W3161731903 type Work @default.
- W3161731903 sameAs 3161731903 @default.
- W3161731903 citedByCount "36" @default.
- W3161731903 countsByYear W31617319032021 @default.
- W3161731903 countsByYear W31617319032022 @default.
- W3161731903 countsByYear W31617319032023 @default.