创造管理新知,造就业界精英,践行持续发展,应对全球挑战。
Our Mission
【2026年11月20日】【管理高等研究院公开学术报告-第168期】一种检测大语言模型生成内容的通用方法
Speaker: Mingjia Mao, University of Delaware
Date & Time: Friday, 20 November 2026, from 14:00 to 15:30 (Beijing Time)
Location: Tongji Building A2101
ABSTRACT
The proliferation of large language models (LLMs) has significantly transformed the digital information landscape, making it increasingly difficult to distinguish human-written from LLM-generated content. Detecting LLM-generated information is essential for preserving trust on digital platforms (e.g., social media and e-commerce sites) and preventing the spread of misinformation, a topic that has garnered significant attention in IS research. However, current detection methods, which primarily focus on identifying content generated by specific LLMs in known domains, face challenges in generalizing to new (i.e., unseen) LLMs and domains. This limitation reduces their effectiveness in real-world applications, where the number of LLMs is rapidly multiplying, and content spans a vast array of domains. In response, we introduce a general LLM detector (GLD) that combines a twin memory network design and a theory-guided detection generalization module to detect LLM-generated information across unseen LLMs and domains. Using real-world datasets, we conduct extensive empirical evaluations and case studies to demonstrate GLD's superiority over state-of-the-art detection methods. The study has important academic and practical implications for digital platforms and LLMs.
Keywords: large language model, detection method, LLM-generated information, generative model, deep learning, memory network, discrepancy mitigation
GUEST BIO
Minjia Mao is a Ph.D. candidate in Financial Services Analytics at the University of Delaware. He holds a B.E. in Materials Science and Engineering from Tsinghua University and an M.S. in Applied Statistics from Xi’an Jiaotong University. His research interests cover design science, machine‑learning optimization, misinformation, AI alignment, and foundational problems of large‑language models. His work has been accepted by *Management Science*, and he has publications in top conferences including AAAI, ICLR, ACL, KDD, and ICIS. He has received multiple academic awards, including the Baidu Big Data and AI Elite Scholarship. He serves as a program committee member and ad hoc reviewer for numerous leading IS and AI conferences.