摘要：Sequential modulations of distractor-related interference (i.e., reduced congruency effect after incongruent as compared to congruent predecessor trials, a.k.a. Gratton effect) have been taken to reflect conflict-induced attentional focusing. To dismiss an alternative interpretation based on integration and retrieval of low-level features, it is important to exert experimental control of stimulus and response feature sequences. This has been achieved by considering only trials associated with complete feature changes. Furthermore, distractors from two different perceptual dimensions, such as stimulus location and shape, have been combined in the same experiment to investigate the question of specificity vs. generality of conflict adaptation. With this method feature sequence control can be exerted, in principle, without disregarding data from feature repetition trials. However, such control may be insufficient when the distractor dimensions overlap semantically. In two experiments we found evidence consistent with the assumption that semantic generalization of stimulus features, such as between a stimulus presented at a left-sided location and a stimulus shape pointing to the left, may yield a between-dimension Gratton effect. These findings raise doubts about inferring generalized attentional conflict adaptation when semantically related distractor dimensions are used.
