AI RESEARCH
Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting
arXiv CS.CL
•
ArXi:2605.20684v1 Announce Type: new Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize for semantic similarity, which frequently surfaces passages that are topically related but lack decision utility, a problem we term the similarity-utility gap. We propose a two-phase non-parametric retrieval architecture that separates high-recall candidate retrieval from high-precision utility ranking.