Building Trustworthy Financial AI: Governance, Bias, and Mechanistic Insights

About

Data Phoenix hosts a talk on building trustworthy financial AI systems, covering governance frameworks, bias detection, and how large language models actually work internally.

Why attend

Fabrizio Dimino explores mechanistic interpretability and positional bias in LLMs—practical knowledge for anyone deploying AI in financial services. You'll learn concrete approaches to AI governance and bias mitigation rather than abstract principles.

Who

Machine learning engineers, AI governance professionals, and financial services teams building or auditing AI systems.