Yanchen Liu


Cambridge, MA, USA 02138
Graduate School of Arts and Sciences, Harvard University

I am a second-year master’s student at Harvard University h.

Currently, I am visiting the Stanford NLP Group s , collaborating with Prof. Diyi Yang. Also, I am a member of the AI4LIFE Group at Harvard SEAS, working with Prof. Hima Lakkaraju.

Previously, I obtained my Bachelor’s degree in Computer Science from TUM tum , with a minor in Computational Linguistics at LMU lmu . During my undergraduate studies, I was fortunate to be supervised by Prof. Hinrich Schütze and Timo Schick at the Center for Information and Language Processing, LMU.

My research interests mainly lie in LLM safety[1][2]. Additionally, I have worked on parameter-efficient adaptation & composition[3][4][5] and retrieval-augmented LLMs[6].


Mar 13, 2024 One paper is accepted to NAACL 2024! :sparkles: drawing
Nov 16, 2023 Greatly honored to give a talk on my work, Dynamic Aggregation & Auto-Discovery of Linguistic Features, within the Stanford NLP Group. :sparkles: pikachu waving
Oct 8, 2023 Two papers are accepted to EMNLP 2023. :sparkles: drawing

selected publications

  1. Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classification
    Yanchen Liu, Srishti Gautam, Jiaqi Ma, and Himabindu Lakkaraju
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics
    NAACL 2024
  2. DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules
    Yanchen LiuWilliam Held, and Diyi Yang
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
    EMNLP 2023
  3. Semantic-Oriented Unlabeled Priming for Large-Scale Language Models
    Yanchen LiuTimo Schick, and Hinrich Schütze
    In ACL Workshop on Simple and Efficient Natural Language Processing, 2022
    ACLW 2023 Oral Presentation