Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'
This addresses the issue of unreliable AI predictions in unfamiliar or adversarial scenarios for users of machine learning systems, but it is a position paper proposing a new paradigm rather than presenting empirical results.
The paper tackles the problem of AI models failing to handle uncertainty and generalize beyond training data, proposing a paradigm shift towards epistemic artificial intelligence using second-order uncertainty measures to improve resilience and robustness.
Despite AI's impressive achievements, including recent advances in generative and large language models, there remains a significant gap in the ability of AI systems to handle uncertainty and generalize beyond their training data. AI models consistently fail to make robust enough predictions when facing unfamiliar or adversarial data. Traditional machine learning approaches struggle to address this issue, due to an overemphasis on data fitting, while current uncertainty quantification approaches suffer from serious limitations. This position paper posits a paradigm shift towards epistemic artificial intelligence, emphasizing the need for models to learn from what they know while at the same time acknowledging their ignorance, using the mathematics of second-order uncertainty measures. This approach, which leverages the expressive power of such measures to efficiently manage uncertainty, offers an effective way to improve the resilience and robustness of AI systems, allowing them to better handle unpredictable real-world environments.