Explainable AI (XAI) is a rapidly growing field that focuses on making artificial intelligence (AI) systems more transparent, interpretable, and understandable to humans. It is becoming increasingly important as AI systems are being used in more decision-making processes that affect people’s lives, such as hiring decisions, loan approvals, and healthcare recommendations. There are many different stakeholders interested in XAI, including individuals who may be affected by the decisions made by AI systems, policymakers, and organizations that develop and use AI.

Despite the importance of explainable AI, there is currently a gap between the research being done within academic contexts and the needs of industry. This gap can be attributed to a variety of factors, including the complexity of real-world AI systems and the challenges of deploying explainable AI in production environments. Bridging this gap will require collaboration between researchers and industry practitioners, as well as the development of new explainability methods that are effective in real-world settings.

In this roundtable discussion, participants will share their perspectives and experiences with explainability methods and will explore the gap between industry and academia in the field of explainability, focusing on the challenges and opportunities presented by this divide.