General Large Language Models (GLLMs) in Derivatives Markets

Éditeurs invités

• Libo Yin, Central University of Finance and Economics
• He Feng, Capital University of Economics and Business

Synthèse

This special issue focuses on the application of general large language models in derivatives markets, exploring how advanced AI systems can extract pricing and risk signals from unstructured textual data. The issue seeks research demonstrating how GLLMs can improve derivatives pricing, hedging strategies, and risk management by analyzing central bank communications, corporate narratives, and other semantic sources that traditionally influence market behavior.

The special issue welcomes empirical and theoretical contributions examining language-based volatility forecasting, sentiment-driven trading strategies, multimodal pricing approaches, and explainable AI methods for derivatives governance. It is particularly interested in work that bridges GLLM capabilities with financial applications such as nowcasting macro shocks, factor discovery, and adaptive risk management in derivatives markets.

Thèmes proposés

• GLLM-Based Risk Factor Discovery in Derivatives Pricing
• Narrative Shocks and Futures Markets
• GLLMs and Tail Risk Estimation in Derivatives
• GLLM-Augmented Delta-Hedging Strategies
• Dynamic Hedging with GLLM-Predicted Sentiment Shifts
• GLLMs for Derivatives Market Microstructure Modeling
• High-Frequency Text Streams and Options Market Reaction
• Multimodal GLLMs in Derivatives
• Cross-Asset Derivatives Strategies Informed by Semantic Correlations
• Regulatory Technology (RegTech) in Derivatives with GLLMs
• Integrating GLLMs with Graph Neural Networks (GNNs) for Derivatives Risk