FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

arXiv·low signal

An expert-guided red-teaming framework for financial LLMs using a two-level taxonomy mapping global standards (FATF, EU DORA) to threats and converting financial documents into context-rich test prompts. An expert-validated rubric cut critical false negatives from 28 to 12 versus standard approaches; it is deployed in South Korea's Financial Security Institute for regulatory sandbox testing. Domain-specific but a useful template for sector-targeted red-teaming.