The Stakeholder Playbook for Explaining AI Systems

Abstract

The purpose of the Stakeholder Playbook is to enable system developers to take into account the different ways in which stakeholders need to "look inside" of the AI/XAI systems. Recent work on Explainable AI has mapped stakeholder categories onto explanation requirements. While most of these mappings seem reasonable, they have been largely speculative. We investigated these matters empirically. We conducted interviews with senior and mid-career professionals possessing post-graduate degrees who had experience with AI and/ or autonomous systems, and who had served in a number of roles including former military, civilian scientists working for the government, scientists working in the private sector, and scientists working as independent consultants. The results show that stakeholders need access to others (e.g., trusted engineers, trusted vendors) to develop satisfying mental models of AI systems. and they need to know "how it fails" and "how it misleads" and not just "how it works." In addition, explanations need to support end-users in performing troubleshooting and maintenance activities, especially as operational situations and input data change. End-users need to be able to anticipate when the AI is approaching an edge case. Stakeholders often need to develop an understanding that enables them to explain the AI to someone else and not just satisfy their own sensemaking. We were surprised that only about half of our Interviewees said they always needed better explanations. This and other findings that are apparently paradoxical can be resolved by acknowledging that different stakeholders have different capabilities, different sensemaking requirements, and different immediate goals. In fact, the concept of “stakeholder” is misleading because the people we interviewed served in a variety of roles simultaneously — we recommend referring to these roles rather than trying to pigeonhole people into unitary categories. Different cognitive styles re another formative factor, as suggested by participant comments to the effect that they preferred to dive in and play with the system rather than being spoon-fed an explanation of how it works. These factors combine to determine what, for each given end-user, constitutes satisfactory and actionable understanding. exp

Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance

“…For example, stakeholders sometimes express a need to be able to trust vendors; they express a need to get explanations from trusted systems engineers. Users need to understand whether they can trust the data that were used to train an AI system (see Hoffman et al, 2022). The measurement scale presented in this article is focused specifically on the end-user's trust in machine-generated explanations.…”

“Minimum Necessary Rigor” in empirically evaluating human–AI work systems

“…In an interview with stakeholders, one of them said that if he could not achieve an understanding of how an AI system works within 10 trials or attempts, then he simply would not use it (Hoffman et al. 2021). Another said that unless a new tool enabled successful performance on 85% of the key tasks on first use, then the tool would not be desired.…”

Reviewing the Ethical Implications of Ai in Decision Making Processes

“…Engaging these stakeholders ensures that ethical guidelines are consistent with existing regulations and helps in shaping future policies on AI ethics (Delgado, et. al., 2021, Hoffman, et. al., 2021, Miller, 2022.…”