Biblio

Due to the migration megatrend, efficient and effective second-language acquisition is vital. One proposed solution involves AI-enabled conversational agents for person-centered interactive language practice. We present results from ongoing action research targeting quality assurance of proprietary generative dialog models trained for virtual job interviews. The action team elicited a set of 38 requirements for which we designed corresponding automated test cases for 15 of particular interest to the evolving solution. Our results show that six of the test case designs can detect meaningful differences between candidate models. While quality assurance of natural language processing applications is complex, we provide initial steps toward an automated framework for machine learning model selection in the context of an evolving conversational agent. Future work will focus on model selection in an MLOps setting.

Though some software development teams are highly effective at delivering security, others either do not care or do not have access to security experts to teach them how. Unfortunately, these latter teams are still responsible for the security of the systems they build: systems that are ever more important to ever more people. We propose that a series of lightweight in-terventions, six hours of facilitated workshops delivered over three months, can improve a team's motivation to consider security and awareness of assurance techniques, changing its security culture even when no security experts are involved. The interventions were developed after an Appreciative Inquiry and Grounded Theory survey of security professionals to find out what approaches work best. They were then validated in fieldwork with a Participatory Action Research study that de-livered the workshops to three development organizations. This approach has the potential to be applied by many development teams, improving the security of software worldwide.