Future of XAI

Explainable Artificial Intelligence (XAI) Concepts

Folkert Stijnman

ML Engineer

Advances in interpretability techniques

As complexity grows, so does the need for XAI
Sophisticated model-agnostic methods
Visualization tools
Interactive interfaces

a screenshot of the title of a paper called XAI for All: Can Large Language Models Simplify Explainable AI?

¹ Mavrepis, P., Makridis, G., Fatouros, G., Koukos, V., Separdani, M. M., & Kyriazis, D. (2024). XAI for All: Can Large Language Models Simplify Explainable AI?. arXiv preprint arXiv:2401.13110.

Addressing the scalability challenge

XAI techniques require lots of computation
XAI should scale with growing usage of AI
Integration with cloud computing

a graphic depicting multiple AI systems

Cross-disciplinary approaches to XAI

graphic showing a group of people from different background working together

Bridge AI with social sciences and humanities
Collaboration between AI researchers, ethicists, psychologists, and social scientists
Incorporate user experience (UX) design

Future challenges

Growth of LLM usage
Increasing regulations, for instance the EU AI act
Important to be aware of privacy concerns, bias and ethical implications of any AI system

graphic showing the future where AI grows

¹ https://artificialintelligenceact.eu/

Let's practice!

Explainable Artificial Intelligence (XAI) Concepts