Accountability Layers: Explaining Complex System Failures by Parts
Abstract
With the rise of AI used for critical decision-making, many important predictions are made by complex and opaque AI algorithms. The aim of eXplainable Artificial Intelligence (XAI) is to make these opaque decision-making algorithms more transparent and trustworthy. This is often done by constructing an ``explainable model'' for a single modality or subsystem. However, this approach fails for complex systems that are made out of multiple parts. In this paper, I discuss how to explain complex system failures. I represent a complex machine as a hierarchical model of introspective sub-systems working together towards a common goal. The subsystems communicate in a common symbolic language. This work creates a set of explanatory accountability layers for trustworthy AI.
BibTeX
@article{Gilpin_2024, title={Accountability Layers: Explaining Complex System Failures by Parts}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26806}, DOI={10.1609/aaai.v37i13.26806}, abstractNote={With the rise of AI used for critical decision-making, many important predictions are made by complex and opaque AI algorithms. The aim of eXplainable Artificial Intelligence (XAI) is to make these opaque decision-making algorithms more transparent and trustworthy. This is often done by constructing an ``explainable model’’ for a single modality or subsystem. However, this approach fails for complex systems that are made out of multiple parts. In this paper, I discuss how to explain complex system failures. I represent a complex machine as a hierarchical model of introspective sub-systems working together towards a common goal. The subsystems communicate in a common symbolic language. This work creates a set of explanatory accountability layers for trustworthy AI.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Gilpin, Leilani H.}, year={2024}, month={Jul.}, pages={15439-15439} }