Publications

2025

  1. tacl_universals.png
    Can Language Models Learn Typologically Implausible Languages?
    Tianyang Xu, Tatsuki Kuribayashi, Yohei Oseki, Ryan Cotterell, and Alex Warstadt
    TACL (to appear), 2025
    arXiv Code
  2. okbench_pipeline.png
    OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking
    Yanhong Li*, Tianyang Xu*, Kenan Tang*, Karen Livescu, David McAllester, and Jiawei Zhou
    Preprint, 2025
    arXiv
  3. surprisal.png
    The Harmonic Structure of Information Contours
    Eleftheria Tsipidi, Samuel Kiegeland, Franz Nowak, Tianyang Xu, Ethan Wilcox, Alex Warstadt, Ryan Cotterell, and Mario Giulianelli
    ACL, 2025
    PDF