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.
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.
More from the studio
1:02:51Tech TalksOperationalizing LLMs: From Prototype to Production
Yogiraj Awati shares how Instacart moves LLM applications beyond prototypes through retrieval, offline and online evaluation, guardrails, observability, and provider fallbacks. Two case studies cover recipe ingestion and Carebot support workflows with API-backed actions and human handoff.
Yogiraj Awati·Sep 17, 2026
1:17:55Tech TalksBeyond the DAG: Building Agentic Workflows That Loop, Branch, and Scale
Agentic workflows loop, branch, retry, and trigger new work instead of following a fixed DAG. Santosh Kumar Radha explains how AgentField uses typed functions, structured outputs, stopping and escalation patterns, event triggers, and controls for scaling, identity, and authorization.
Santosh Kumar Radha·Sep 17, 2026
1:05:16Tech TalksSecuring Code You Didn't Write: The AI Era's New Threat Model
Coding agents expand the software supply chain to include repositories, configuration, comments, connectors, and tool output. Rome Thorstenson examines reported attacks and outlines practical controls for permissions, secrets, prompt injection, and defense in depth.
Rome Thorstenson·Sep 17, 2026