In this article, we suggest that the study of social interactions and the development of a “sense of agency” in joint action can help determine the content of relevant explanations to be implemented in artificial systems to make them “explainable.” The introduction of automated systems, and more broadly of Artificial Intelligence, into many domains has profoundly changed the nature of human activity, as well as the subjective experience that agents have of their own actions and their consequences – an experience (...) that is commonly referred to as sense of agency. We propose to examine the empirical evidence supporting this impact of automation on individuals’ sense of agency, and hence on measures as diverse as operator performance, system explicability and acceptability. Because of some of its key characteristics, AI occupies a special status in the artificial systems landscape. We suggest that this status prompts us to reconsider human–AI interactions in the light of human–human relations. We approach the study of joint actions in human social interactions to deduce what key features are necessary for the development of a reliable sense of agency in a social context and suggest that such framework can help define what constitutes a good explanation. Finally, we propose possible directions to improve human–AI interactions and, in particular, to restore the sense of agency of human operators, improve their confidence in the decisions made by artificial agents, and increase the acceptability of such agents. (shrink)

The goal of this study is to characterize observers’ abilities to discriminate between endogenous and exogenous changes. To do so, we developed a new experimental paradigm. On each trial, participants were shown a dot pattern on the screen. Next, the pattern disappeared and participants were to reproduce it. Changes were surreptuously introduced in the stimulus, either by presenting participants anew with the dot pattern they had themselves produced on the previous trial or by presenting participants with a slightly different dot (...) pattern . We analyzed awareness of the changes and behavioral adaptation to them in a dynamical manner. We observe signal attenuation in the presence of endogenous change, dissociation between self-attribution reports and behavioral effect of agency. We discuss the source of this sensitive attenuation as well as the relation between a minimal or core self and an extended, narrative or autobiographical self. (shrink)

The goal of this study is to characterize observers’ abilities to detect gradual changes and to explore putative dissociations between conscious experience of change and behavioral adaptation to a changing stimulus. We developed a new experimental paradigm in which, on each trial, participants were shown a dot pattern on the screen. Next, the pattern disappeared and participants had to reproduce it. In some conditions, the target pattern was incrementally rotated over successive trials and participants were either informed or not of (...) this change. We analyzed both awareness of the changes and the dynamics of behavioral adaptation, in a way that makes it possible to assess both variability and accuracy as they change over time. Results indicate a dissociation between change awareness and behavioral adaptation to the changes, and support the notion that unconscious representations of visual stimuli are more precise and detailed than previously suggested. We discuss the implications of these results for theories of change detection. (shrink)

Cognitive fatigue is a problem for the safety of critical systems as it can lead to accidents, especially during unexpected events. In order to determine the extent to which it disrupts adaptive capabilities, we evaluated its effect on online and anticipatory control. Despite numerous studies conducted to determine its effects, the exact mechanism affected by fatigue remains to be clarified. In this study, we used distribution and electromyographic analysis to assess whether cognitive fatigue increases the capture of the incorrect automatic (...) response or if it impairs its suppression, and whether the conflict adaptation effect is reduced. To this end, we evaluated the evolution of the performance over time during the Simon task, a classic conflict task that elicits incorrect automatic responses. To accentuate the presence of fatigue during the Simon task, two groups previously performed a dual-task with two different cognitive load levels to create two different levels of fatigue. The results revealed that time on task impaired online control by disrupting the capacity to suppress the incorrect response but leaving unaffected the expression of the automatic response. Furthermore, participants emphasized speed rather than accuracy with time on task, with in addition more fast guesses, suggesting that they opted for a less effortful response strategy. As the implementation of the suppression mechanism requires cognitive effort, the conjunction of these results suggests that the deficits observed may be due to disengagement of effort over time rather than reflecting an incapacity to make an effort. (shrink)