Exploring real‑deployment of generative models in finance, practical challenges, evaluation strategies including for LLM‑generated outputs, and agentic pipeline assessment.
Overview
The talk will discuss the reality of building applications with generative models in environments that demand high quality and actionable responses in production. We’ll be going into our particular challenge of creating an application within the very domain-driven space we are working in (financial). We’ll also discuss strategies we are building to evaluate the output of generated by leveraging LLMs, and challenges around LLM evaluations for agentic pipelines.
