On September 25, 2025, at 14:30 PM, the 50th Forum on Digital Technology and Economic Finance Frontiers was successfully held. The theme of the lecture was "When Optimism Breeds Risk: Evidence from LLM-Analyzed Fund Manager Forecasts", was successfully convened in Room 408, South Wenquan Building. The lecture was delivered by Professor Jia Liu, currently affiliated with University of Portsmouth. It was hosted by Professor Xianming Sun , the director of the Department of Financial Engineering and the leader of Master's Tutor Group of Zhongnan University of Economics and Law and Deputy Director of the Innovation and Talent Base for Digital Technology and Finance. Over 30 faculty members and students from the School of Finance participated in the lecture in person.

The lecture officially kicked off after a brief opening speech by Professor Xianming Sun . Professor Jia Liu first introduced a new framework for sentiment analysis based on large language models, LLM-MESA, which can be used to achieve fine grain and materialized sentiment measurement of financial texts. The research team applied this method to mutual fund managers' reports to extract their expected sentiment towards stocks, macroeconomics, and bonds, revealing for the first time how institutional investors' stock market sentiment predicts the risk of market crashes.

Professor Liu pointed out that his research found that fund managers' optimistic outlook on stocks significantly increases the risk of crashes, indicating that irrational emotions are embedded in institutional forecasts. This effect is particularly pronounced in the case of low-skill funds, pessimistic macroeconomic expectations, and optimistic views in the bond market. Intermediary analysis further shows that optimism amplifies institutional herding and attracts sentiment-driven retail investors, thereby exacerbating market vulnerabilities.

Subsequently, Professor Jia Liu deeply analyzed the practical significance of the development of large language models to the financial industry. She pointed out that text analysis technology based on large language models not only provides Financial Institution Groups with more accurate sentiment monitoring tools, but also has broad application prospects in the fields of risk management, investment decision-making, and regulatory technology. Especially in the context of the rapid development of digital finance, this technology helps institutions to identify changes in market sentiment in a more timely manner and improve risk early warning capabilities.

During the interactive Q&A session, teachers and students on site had in-depth discussions on the construction details of the LLM-MESA model, the robustness of sentiment indicators, and the measurement methods of institutional herd behavior. The participating teachers and students expressed that this lecture deepened their understanding of the irrational behavior of institutional investors and its market impact, providing an important reference for the study of market stability mechanisms and related policy design.

Finally, Professor Xianming Sun  expressed his gratitude to Professor Jia Liu for his wonderful sharing, and pointed out that financial text analysis based on large language models is an important direction of digital finance research, with broad application prospects in the fields of risk early warning and behavior supervision, and will continue to promote research and cooperation in this direction in the future. With this, the lecture concluded successfully.

Speaker Introduction

Jia Liu, Fellow of the British Academy of Management, Professor of Accounting and Finance at the University of Portsmouth. She obtained her PhD from the University of Birmingham, UK, and previously held academic positions at the University of Leeds and the University of Salford.Her research interests include corporate finance, behavioral finance, financial markets, risk management, fintech, big data, accounting reporting and disclosure, and sustainability.She has published over 80 academic papers in leading international journals in finance, accounting, and management, including nearly 20 in ABS-4 and FT50 journals; and has published monographs on corporate governance, sustainability, and decision-making. She has received "Best Paper Awards" from the European Management Journal (EMJ), the British Academy of Management (UK), the Southwestern Finance Association (USA), and the Eurasian Business and Economics Society (EBES). Her research has been featured and covered by various media outlets, including the renowned The Conversation, The Washington Post, and NASDAQ Stock Exchange.

Frontier Forum for Digital Technology and Finance introduction

Recent years have witnessed a dramatic acceleration in a digital revolution in economic sectors and a rapid adoption of the new generation of information technologies, such as artificial intelligence, blockchain, cloud computing, big data, etc. These technologies effectively set off the digital economy. It has become a key driving force in creating global economic growth, improving the modernization level of governance capabilities, and promoting high-quality economic development in China. In particular, digital finance is the most important part of the digital economy. To explore the development direction of the cross-integration of digital technology and finance, the Innovation and Talent Base for Digital Technology and Finance is hosting the “Frontier Forum for Digital Technology and Finance”, in collaboration with the School of Finance, Wenlan School of Business, Economics School, School of Information and Safety Engineering, School of Statistics and Mathematics, School of Public Finance and Taxation of Zhongnan University of Economics and Law (ZUEL). This lecture series will invite the well-known scholars at home and abroad in digital technology, digital economy, digital finance, and other related fields as guest speakers, providing an open and cutting-edge academic exchange platform for interdisciplinary research on digital technology and finance.