Mingqian Zheng 郑鸣谦

prof_pic.jpg

Hi there!

I am a Ph.D. student in LTI at Carnegie Mellon University, co-advised by Carolyn Rosé and Maarten Sap. I am broadly interested in Natural Language Processing and Computational Social Science.

Previously, I completed my Master’s in Survey and Data Science at the University of Michigan, where I was advised by Yajuan Si. I conducted research on NLP with David Jurgens in the Blablablab and also worked with David Flood as a member of the HPACC team. Prior to that, I got my Bachelor’s at NYU Shanghai with double majors in Mathematics and Data Science (Computer Science Concentration), where I worked with Hongyi Wen on Recommendation Systems.

news

Jun 23, 2025 Gave an invited talk at Pareto.ai about our recent work on LLM refusals.
Sep 19, 2024 My first paper got accepted to the Findings of EMNLP 2024! See you in Miami!🌴
Aug 26, 2024 Starting my new life chapter at CMU LTI as a PhD student!

selected publications

  1. EMNLP Findings
    When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models
    Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, and 2 more authors
    arXiv preprint arXiv:2311.10054, 2024
  2. NAACL 2025
    Causally Modeling the Linguistic and Social Factors that Predict Email Response
    Yinuo Xu*, Hong Chen*, Sushrita Rakshit*, and 14 more authors
    Sep 2024
  3. preprint
    Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
    Mingqian Zheng, Wenjia Hu, Patrick Zhao, and 5 more authors
    Sep 2025
  4. preprint
    Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics
    Jiarui Liu, Yueqi Song*, Yunze Xiao*, and 5 more authors
    Sep 2025