Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214851743> ?p ?o ?g. }
- W4214851743 endingPage "33" @default.
- W4214851743 startingPage "1" @default.
- W4214851743 abstract "Would you allow an AI agent to make decisions on your behalf? If the answer is “not always,” the next question becomes “in what circumstances”? Answering this question requires human users to be able to assess an AI agent—and not just with overall pass/fail assessments or statistics. Here users need to be able to localize an agent’s bugs so that they can determine when they are willing to rely on the agent and when they are not. After-Action Review for AI (AAR/AI), a new AI assessment process for integration with Explainable AI systems, aims to support human users in this endeavor, and in this article we empirically investigate AAR/AI’s effectiveness with domain-knowledgeable users. Our results show that AAR/AI participants not only located significantly more bugs than non-AAR/AI participants did (i.e., showed greater recall) but also located them more precisely (i.e., with greater precision). In fact, AAR/AI participants outperformed non-AAR/AI participants on every bug and were, on average, almost six times as likely as non-AAR/AI participants to find any particular bug. Finally, evidence suggests that incorporating labeling into the AAR/AI process may encourage domain-knowledgeable users to abstract above individual instances of bugs; we hypothesize that doing so may have contributed further to AAR/AI participants’ effectiveness." @default.
- W4214851743 created "2022-03-05" @default.
- W4214851743 creator A5003486714 @default.
- W4214851743 creator A5011173372 @default.
- W4214851743 creator A5022959741 @default.
- W4214851743 creator A5030052689 @default.
- W4214851743 creator A5042350842 @default.
- W4214851743 creator A5053090744 @default.
- W4214851743 creator A5053324798 @default.
- W4214851743 creator A5061223981 @default.
- W4214851743 creator A5062639832 @default.
- W4214851743 creator A5078508343 @default.
- W4214851743 creator A5081015851 @default.
- W4214851743 creator A5089733422 @default.
- W4214851743 date "2022-03-04" @default.
- W4214851743 modified "2023-10-18" @default.
- W4214851743 title "Finding AI’s Faults with AAR/AI: An Empirical Study" @default.
- W4214851743 cites W1981015521 @default.
- W4214851743 cites W1994606570 @default.
- W4214851743 cites W2036779186 @default.
- W4214851743 cites W2053075547 @default.
- W4214851743 cites W2060935106 @default.
- W4214851743 cites W2062588940 @default.
- W4214851743 cites W2084429940 @default.
- W4214851743 cites W2087061903 @default.
- W4214851743 cites W2090464375 @default.
- W4214851743 cites W2090645352 @default.
- W4214851743 cites W2096036274 @default.
- W4214851743 cites W2097695938 @default.
- W4214851743 cites W2103051026 @default.
- W4214851743 cites W2114315281 @default.
- W4214851743 cites W2131251708 @default.
- W4214851743 cites W2140995456 @default.
- W4214851743 cites W2142225512 @default.
- W4214851743 cites W2145071552 @default.
- W4214851743 cites W2157289187 @default.
- W4214851743 cites W2346760997 @default.
- W4214851743 cites W2595640485 @default.
- W4214851743 cites W2611274842 @default.
- W4214851743 cites W2620350838 @default.
- W4214851743 cites W2789415069 @default.
- W4214851743 cites W2795530988 @default.
- W4214851743 cites W2807298419 @default.
- W4214851743 cites W2891548690 @default.
- W4214851743 cites W2892051885 @default.
- W4214851743 cites W2893622216 @default.
- W4214851743 cites W2902634493 @default.
- W4214851743 cites W2915124689 @default.
- W4214851743 cites W2916904544 @default.
- W4214851743 cites W2942444880 @default.
- W4214851743 cites W2949858875 @default.
- W4214851743 cites W2963123635 @default.
- W4214851743 cites W2963214037 @default.
- W4214851743 cites W2964135091 @default.
- W4214851743 cites W2964277809 @default.
- W4214851743 cites W2966362896 @default.
- W4214851743 cites W2990540492 @default.
- W4214851743 cites W3010499686 @default.
- W4214851743 cites W3032875465 @default.
- W4214851743 cites W3040729482 @default.
- W4214851743 cites W3081859834 @default.
- W4214851743 cites W3156666346 @default.
- W4214851743 cites W3197450565 @default.
- W4214851743 cites W4239816899 @default.
- W4214851743 cites W4288359828 @default.
- W4214851743 cites W4291213652 @default.
- W4214851743 cites W4299335686 @default.
- W4214851743 cites W4299627282 @default.
- W4214851743 doi "https://doi.org/10.1145/3487065" @default.
- W4214851743 hasPublicationYear "2022" @default.
- W4214851743 type Work @default.
- W4214851743 citedByCount "4" @default.
- W4214851743 countsByYear W42148517432022 @default.
- W4214851743 countsByYear W42148517432023 @default.
- W4214851743 crossrefType "journal-article" @default.
- W4214851743 hasAuthorship W4214851743A5003486714 @default.
- W4214851743 hasAuthorship W4214851743A5011173372 @default.
- W4214851743 hasAuthorship W4214851743A5022959741 @default.
- W4214851743 hasAuthorship W4214851743A5030052689 @default.
- W4214851743 hasAuthorship W4214851743A5042350842 @default.
- W4214851743 hasAuthorship W4214851743A5053090744 @default.
- W4214851743 hasAuthorship W4214851743A5053324798 @default.
- W4214851743 hasAuthorship W4214851743A5061223981 @default.
- W4214851743 hasAuthorship W4214851743A5062639832 @default.
- W4214851743 hasAuthorship W4214851743A5078508343 @default.
- W4214851743 hasAuthorship W4214851743A5081015851 @default.
- W4214851743 hasAuthorship W4214851743A5089733422 @default.
- W4214851743 hasConcept C100660578 @default.
- W4214851743 hasConcept C119857082 @default.
- W4214851743 hasConcept C134306372 @default.
- W4214851743 hasConcept C154945302 @default.
- W4214851743 hasConcept C15744967 @default.
- W4214851743 hasConcept C180747234 @default.
- W4214851743 hasConcept C33923547 @default.
- W4214851743 hasConcept C36503486 @default.
- W4214851743 hasConcept C41008148 @default.
- W4214851743 hasConceptScore W4214851743C100660578 @default.
- W4214851743 hasConceptScore W4214851743C119857082 @default.