Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022425370> ?p ?o ?g. }
- W3022425370 abstract "Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system." @default.
- W3022425370 created "2020-05-13" @default.
- W3022425370 creator A5017484756 @default.
- W3022425370 creator A5038455119 @default.
- W3022425370 creator A5051058850 @default.
- W3022425370 creator A5055095298 @default.
- W3022425370 creator A5058250216 @default.
- W3022425370 creator A5090930182 @default.
- W3022425370 date "2020-05-05" @default.
- W3022425370 modified "2023-10-15" @default.
- W3022425370 title "Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition" @default.
- W3022425370 cites W1934515642 @default.
- W3022425370 cites W1969169704 @default.
- W3022425370 cites W1994606570 @default.
- W3022425370 cites W1998622795 @default.
- W3022425370 cites W2010158189 @default.
- W3022425370 cites W2017131938 @default.
- W3022425370 cites W2020584411 @default.
- W3022425370 cites W2027103861 @default.
- W3022425370 cites W2027280740 @default.
- W3022425370 cites W2041029272 @default.
- W3022425370 cites W2050836750 @default.
- W3022425370 cites W2063052894 @default.
- W3022425370 cites W2091455316 @default.
- W3022425370 cites W2096434649 @default.
- W3022425370 cites W2097117768 @default.
- W3022425370 cites W2110575115 @default.
- W3022425370 cites W2111078031 @default.
- W3022425370 cites W2119858020 @default.
- W3022425370 cites W2124002192 @default.
- W3022425370 cites W2129230445 @default.
- W3022425370 cites W2137606182 @default.
- W3022425370 cites W2146948596 @default.
- W3022425370 cites W2152184085 @default.
- W3022425370 cites W2154157725 @default.
- W3022425370 cites W2237502368 @default.
- W3022425370 cites W2270696664 @default.
- W3022425370 cites W2282821441 @default.
- W3022425370 cites W2295883547 @default.
- W3022425370 cites W2332488709 @default.
- W3022425370 cites W2394669110 @default.
- W3022425370 cites W2513376386 @default.
- W3022425370 cites W2554751554 @default.
- W3022425370 cites W2591878254 @default.
- W3022425370 cites W2607223307 @default.
- W3022425370 cites W2612412344 @default.
- W3022425370 cites W2613800022 @default.
- W3022425370 cites W2613800395 @default.
- W3022425370 cites W2657631929 @default.
- W3022425370 cites W2751298778 @default.
- W3022425370 cites W2770804203 @default.
- W3022425370 cites W2777647957 @default.
- W3022425370 cites W2780414687 @default.
- W3022425370 cites W2781474777 @default.
- W3022425370 cites W2788403449 @default.
- W3022425370 cites W2788730650 @default.
- W3022425370 cites W2790505917 @default.
- W3022425370 cites W2794542628 @default.
- W3022425370 cites W2795530988 @default.
- W3022425370 cites W2802935654 @default.
- W3022425370 cites W283954808 @default.
- W3022425370 cites W2886614482 @default.
- W3022425370 cites W2888580379 @default.
- W3022425370 cites W2891503716 @default.
- W3022425370 cites W2896215772 @default.
- W3022425370 cites W2897990074 @default.
- W3022425370 cites W2902784621 @default.
- W3022425370 cites W2902901408 @default.
- W3022425370 cites W2903808828 @default.
- W3022425370 cites W2915577650 @default.
- W3022425370 cites W2916797267 @default.
- W3022425370 cites W2918817626 @default.
- W3022425370 cites W2921712231 @default.
- W3022425370 cites W2922531677 @default.
- W3022425370 cites W2928398266 @default.
- W3022425370 cites W2929292817 @default.
- W3022425370 cites W2932286353 @default.
- W3022425370 cites W2942103387 @default.
- W3022425370 cites W2942157335 @default.
- W3022425370 cites W2942444880 @default.
- W3022425370 cites W2943745370 @default.
- W3022425370 cites W2948516495 @default.
- W3022425370 cites W2950772592 @default.
- W3022425370 cites W2960259221 @default.
- W3022425370 cites W2962772482 @default.
- W3022425370 cites W2962790223 @default.
- W3022425370 cites W2963214037 @default.
- W3022425370 cites W2963233086 @default.
- W3022425370 cites W2963399068 @default.
- W3022425370 cites W2963424940 @default.
- W3022425370 cites W2963715038 @default.
- W3022425370 cites W2964027122 @default.
- W3022425370 cites W2969224142 @default.
- W3022425370 cites W2969521705 @default.
- W3022425370 cites W2992457155 @default.
- W3022425370 cites W2992923261 @default.
- W3022425370 cites W2995188596 @default.
- W3022425370 cites W2996061341 @default.
- W3022425370 cites W2998004401 @default.
- W3022425370 cites W3028765225 @default.