Yanchen Liu

CV

Cambridge, MA, USA 02139
Schwarzman College of Computing, MIT

Hi all! I am a 2nd-year PhD student at mit MIT IDSS and CSAIL, advised by Prof. Dylan Hadfield-Menell. My research was generously supported by the MIT Michael Hammer Fellowship.

Previously, I obtained my Master’s degree from h Harvard University, where I worked with Prof. Hima Lakkaraju and my Bachelor’s degree in Computer Science from tum TUM, with a minor in Computational Linguistics at lmu LMU, supervised by Prof. Hinrich Schütze. Also, I had the opportunity to visit the s Stanford NLP Group, collaborating with Prof. Diyi Yang for one year.

My research interests mainly lie in scalable supervision and scalable oversight, i.e., how to train and oversee superhuman-level AI systems.

Massachusetts Institute of Technology Ph.D. student, IDSS & CSAIL
Harvard University S.M. in Data Science

news

Nov 4, 2026 New blog post: The Evaluator Dilemma – Does Recursive Self-Improvement Really Improve?, with an audit registry of ten published self-improving AI systems. :sparkles:
Sep 23, 2025 I have started my PhD at MIT! :sparkles: drawing
Sep 20, 2024 One paper is accepted to EMNLP 2024! See you in Miami! :sparkles: 🎉

experience

2025 – Present
MITIDSS & CSAILPh.D. student Advised by Dylan Hadfield-Menell.
2023 – 2024
Stanford NLP GroupVisiting student Advised by Diyi Yang.
2022 – 2024
Harvard UniversityS.M. in Data Science Advised by Hima Lakkaraju.
2018 – 2022
Technical University of MunichB.Sc. in Computer Science Minor in Computational Linguistics at LMU, advised by Hinrich Schütze.




selected publications All publications →

* equal contribution. Full list on Google Scholar.

  1. Blog post
    The Evaluator Dilemma: Does Recursive Self-Improvement Really Improve?
    Yanchen Liu
  2. NeurIPS 2024 249
    PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
    Yijia Shao, Tianshi Li, Weiyan Shi, Yanchen Liu, and Diyi Yang
  3. EMNLP 2024 13
    Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach
    Yanchen Liu, Mingyu Derek Ma, Wenna Qin, Azure Zhou, Jiaao Chen, Weiyan Shi, Wei Wang, and Diyi Yang
  4. NAACL 2024 62
    Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classification
    Yanchen Liu, Srishti Gautam, Jiaqi Ma, and Himabindu Lakkaraju
  5. EMNLP 2023 23
    DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules
    Yanchen Liu, William Held, and Diyi Yang
  6. ACLW 2023 17
    Semantic-Oriented Unlabeled Priming for Large-Scale Language Models
    Yanchen Liu, Timo Schick, and Hinrich Schütze

honors & awards

2025 MIT Michael Hammer Fellowship
2022 Finalist, Best Paper Award in Mechatronics, ICMA 2022

talks

Nov 2023 Dynamic Aggregation & Auto-Discovery of Linguistic Features
Stanford NLP Group · Slides