SimVBG: Simulating Individual Values by Backstory Generation
EMNLP 2025 Main Conference
research.log LLMs -> individuals
杜邦得
Ph.D. Student, Department of Computer Science and Technology, Tsinghua University
I study how large language models can understand, empower, and model individuals.
About
I am a Ph.D. student at THUIR, Department of Computer Science and Technology, Tsinghua University, advised by Prof. Yiqun Liu.
My research centers on how large language models can understand, empower, and model individuals, with interests in evaluation, personalization, digital twins, and human-centered AI systems. I am always happy to connect and collaborate with fellow researchers and engineers.
我是清华大学计算机科学与技术系 THUIR 的博士生,导师为 刘奕群教授。
我的研究关注大语言模型如何理解、赋能并建模个体,兴趣包括评测、个性化、数字孪生与以人为中心的 AI 系统。欢迎学术与工程合作交流。
Selected Publications
See the full and most recent list on Google Scholar.
完整和最新论文列表见 Google Scholar。
EMNLP 2025 Main Conference
ACL 2026 Findings
SIGIR 2025
Scientific Reports, 2025
KDD 2026
ICML 2026
News
The hallucination neuroimaging study was accepted to ICML 2026.
The public opinion simulation paper was accepted to KDD 2026.
TwinVoice was accepted to ACL 2026 Findings.
SimVBG was accepted to EMNLP 2025 Main Conference.
The EEG study on polarized short-video content was published in Scientific Reports.
Education
Ph.D. Student, Department of Computer Science and Technology
B.Eng., Department of Automation
Gaokao: 701, National Paper II, 2019.
Awards
2026
2022
First author
Contact