Explainable AI does not provide the explanations end-users are asking for
Explainable Artificial Intelligence (XAI) techniques are frequently required by users in many AI systems with the goal of understanding complex models, their associated predictions, and gaining trust. While suitable for some specific tasks during development, their adoption by organisations to enhance trust in machine learning systems has unintended consequences. In this paper we discuss XAI's limitations in deployment and conclude that transparency alongside with rigorous validation are better suited to gaining trust in AI systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Similar Papers 제목 키워드 기반
Stability of Explainable Recommendation
Explainable Recommendation has been gaining attention over the last few years in industry and academia. Explanations provided along with recommendations in a recommender system framework have many uses: particularly reas…
Explainable ModelsExplainable RecommendationRecommendation SystemsDisentangling Likes and Dislikes in Personalized Generative Explainable Recommendation
Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between the predicted and ground-truth explanatio…
Explainable RecommendationText GenerationIXAII: An Interactive Explainable Artificial Intelligence Interface for Decision Support Systems
Although several post-hoc methods for explainable AI have been developed, most are static and neglect the user perspective, limiting their effectiveness for the target audience. In response, we developed the interactive …
Explainable artificial intelligenceWhat Does Explainable AI Really Mean? A New Conceptualization of Perspectives
We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its …
Interactive Explanation with Varying Level of Details in an Explainable Scientific Literature Recommender System
Explainable recommender systems (RS) have traditionally followed a one-size-fits-all approach, delivering the same explanation level of detail to each user, without considering their individual needs and goals. Further, …
Explainable RecommendationRecommendation Systems