LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline

TL;DR

This paper presents a transparent LLM-based pipeline for macro-financial stress testing that generates coherent, country-specific scenarios to assess portfolio risk, offering a scalable and interpretable alternative to traditional methods.

Contribution

The paper introduces a novel hybrid prompt-RAG pipeline for generating auditable macroeconomic stress scenarios, enhancing transparency and reproducibility in financial risk assessment.

Findings

LLM-generated scenarios produce stable tail-risk amplification.

Risk variation is mainly driven by portfolio composition and prompt design.

The pipeline ensures reproducibility through snapshotting and hash verification.

Abstract

We develop a transparent and fully auditable LLM-based pipeline for macro-financial stress testing, combining structured prompting with optional retrieval of country fundamentals and news. The system generates machine-readable macroeconomic scenarios for the G7, which cover GDP growth, inflation, and policy rates, and are translated into portfolio losses through a factor-based mapping that enables Value-at-Risk and Expected Shortfall assessment relative to classical econometric baselines. Across models, countries, and retrieval settings, the LLMs produce coherent and country-specific stress narratives, yielding stable tail-risk amplification with limited sensitivity to retrieval choices. Comprehensive plausibility checks, scenario diagnostics, and ANOVA-based variance decomposition show that risk variation is driven primarily by portfolio composition and prompt design rather than by the retrieval mechanism. The pipeline incorporates snapshotting, deterministic modes, and hash-verified artifacts to ensure reproducibility and auditability. Overall, the results demonstrate that LLM-generated macro scenarios, when paired with transparent structure and rigorous validation, can provide a scalable and interpretable complement to traditional stress-testing frameworks.