Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting

TL;DR

This paper introduces a two-phase retrieval system for corporate credit analysis that improves the relevance of extracted information from complex financial documents, reducing review time significantly.

Contribution

It presents a novel non-parametric, utility-focused retrieval architecture that separates candidate retrieval from utility ranking, tailored for multilingual, document-heavy financial analysis.

Findings

Outperforms naive retrieval baselines on proprietary multilingual financial documents.

Reduces document review time from hours to about three minutes in real-world deployment.

Enhances decision-support workflows with a utility-aware retrieval approach.

Abstract

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. The first phase combines lexical and dense multilingual retrieval to construct a broad candidate pool. The second phase applies an adaptive retrieval controller that filters candidates using query intent and document structure signals, followed by an LLM-as-a-Judge utility scoring mechanism that ranks passages by analytical usefulness rather than semantic proximity. A context-aware extraction module preserves structural fidelity across narrative text and complex financial tables. The system is deployed entirely on-premise to satisfy enterprise data governance requirements. Evaluated on a multilingual corpus of proprietary financial documents with analyst-curated relevance labels, the system significantly outperforms naive retrieval baselines. In production deployment across more than 800 credit analysts, document review time was reduced from several hours to approximately three minutes, demonstrating the practical value of utility-aware RAG architectures for document-intensive decision-support workflows.