Research on the Impact Mechanism of the Fusion Model on Stock Valuation Correction and Market Risk Forecasting in an Uncertain Environment

Abstract

Under geopolitical tensions and monetary policy shifts, global stock market volatility has intensified. Traditional valuation models and risk forecasting models, relying on historical static parameters and overlooking non-quantitative information such as management tone, suffer from systematic biases. This study uses the Chinese financial language model SilverSight and its ASSL framework as the core information-extraction tool and builds a fusion model. The integrated framework reconstructs asset pricing logic via a three-tier mechanism: extracting three types of complementary signals via ASSL, embedding them into DCF and GARCH-X as time-varying adjustments, and constructing a simultaneous equation system to reveal synergistic effects. Theoretical analysis indicates that the proposed framework transcends the conventional reliance on structured quantitative data and improves the accuracy of stock intrinsic value estimation and the forward-lovingness of market volatility forecasting through text-enhanced dynamic parameter adjustment. This study contributes a novel methodological pathway for the deep integration of large language models with asset pricing theory under uncertainty and a theoretical foundation for investors to leverage Chinese financial LLMs to enhance firm valuation and risk assessment.