Next upHack for Humanity: San Francisco (powered by Google Gemini)
Tech Talks · 48:04

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

Fabrizio Dimino examines why financial LLM recommendations can change when option order changes. He connects positional-bias tests and mechanistic interpretability with finance-specific red teaming, risk-sensitive scoring, model validation, and AI governance.

Fabrizio Dimino
Fabrizio Dimino
Sep 17, 2026
Summary

Financial AI can sound objective while responding to surface features such as the order of options. Fabrizio Dimino presents two research projects that test this gap from different angles. The first measures positional bias and uses direct logit attribution, logit lens analysis, and attention-head ablation to trace where preferences emerge. The second examines adversarial robustness through a finance-specific benchmark, multi-turn attacks, ensemble judging, and severity-aware scoring. Together, the projects frame trustworthy financial AI as a measurement and governance problem, with option randomization, bias tracking, and stress testing as practical controls.