An LLM-Enhanced Multimodal Graph Learning Framework for Enterprise Risk Prediction

TOPIC	An LLM-Enhanced Multimodal Graph Learning Framework for Enterprise Risk Prediction
TIME&DATE	10:30 am - 12:00 pm, December 4, 2025 (Thursday)
Venue	Room D604, Teaching Complex D Building
Speaker	Dongcheng Zhang CUHK Business School
Abstract	Enterprise risk prediction is critical for informed investment decision-making, yet it remains challenging because it requires modeling multimodal information (e.g., structured financial indicators and unstructured text) as well as the complex interrelationships among companies and institutions. Existing methods often process these modalities in isolation or struggle to capture implicit and higher-order dependencies. To address these limitations, we propose a unified framework that integrates the strengths of large language models (LLMs) and graph learning for enterprise risk prediction using multimodal data sources. Specifically, we design a multi-stage Chain-of-Thought prompting strategy that enables LLMs to generate risk-aware textual summaries from each company’s business descriptions, financial indicators, and investor profiles. These semantic representations are fused with other structured features through a multimodal encoder. To model inter-company dependencies, we construct graphs using both investment relationships and LLM-generated summaries. Given the subtle and implicit nature of these dependencies, we introduce an adjacency augmentation mechanism that captures meaningful high-order relations and supports efficient information propagation while mitigating the over-smoothing issue in graph neural networks. Comprehensive experiments on real-world datasets spanning multiple years and markets demonstrate the superiority of our method. Overall, the proposed approach provides a novel and general LLM-enhanced multimodal graph learning framework for enterprise risk prediction.
Biography	Dongcheng Zhang is an Assistant Professor at the Department of Decisions, Operations and Technology in the Chinese University of Hong Kong (CUHK) Business School. Prior to joining CUHK, he was a post-doctoral fellow at the Goizueta Business School of Emory University. He received his Ph.D. in Management Science and Engineering, BE in Engineering, and BA in Management from Tsinghua University. His research focuses on developing and applying machine learning algorithms, statistical methods, and analytical models to improve decision-making in digital marketing and management information systems. In particular, he is interested in developing interpretable and theory-driven machine learning/deep learning algorithms for substantive business problems (e.g., text mining, consumer choices, and FinTech).