Presentations

A list of conference presentations and invited talks. An asterisk (*) indicates equal contribution.

2025

  1. SCiL
    Do LLMs Understand Anaphoric Accessibility?
    Xiaomeng Zhu*, Zhenghao Herbert Zhou*, Simon Charlow, and Robert Frank
    Poster presented at the Society for Computation in Linguistics 2025 (SCiL), Eugene, OR, Jul 2025
  2. YaleAISymposium
    Understanding the abilities of AI systems
    R. Thomas McCoy, and Zhenghao Herbert Zhou
    Poster presented at the Envisioning AI at Yale: An Interdisciplinary Symposium 2025, New Haven, CT, May 2025
    Poster
  3. YaleAISymposium
    How to evaluate large language models: Insights from linguistics
    R. Thomas McCoy, and Zhenghao Herbert Zhou
    Poster presented at the Envisioning AI at Yale: An Interdisciplinary Symposium 2025, New Haven, CT, May 2025
    Poster
  4. NAACL
    Is In-Context Learning a Type of Error-Driven Learning Mechanism? Evidence from the Inverse Frequency Effects in Structural Priming
    Zhenghao Zhou, Robert Frank, and R. Thomas McCoy
    Talk presented at the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Albuquerque, NM, Apr 2025
    Slides
  5. LSA
    Error-Driven Learning in DFT: A case study of structural priming
    Zhenghao Herbert Zhou
    Talk presented at the Linguistic Society of America 2025 Annual Meeting (LSA), Philadelphia, PA, Jan 2025
    Slides

2024

  1. Invited Talk
    Is In-Context Learning a Type of Error-Driven Learning Mechanism? Evidence from the Inverse Frequency Effects in Structural Priming
    Zhenghao Herbert Zhou
    Invited talk presented at the Hollymartin Lab at the University of Edinburgh, Edinburgh, UK, Dec 2024
    Slides
  2. AMLaP
    Is In-Context Learning a Type of Error-Driven Learning Mechanism? Diagnosing with the Inverse Frequency Effects in Structural Priming
    Zhenghao Zhou, Robert Frank, and R. Thomas McCoy
    Poster presented at the 30th Architecture and Mechanisms for Language Processing (AMLaP), Edinburgh, UK, Sep 2024
    PDF Poster
  3. ESSLLI
    Language Models Show Gradient Inverse Frequency Effects in Structural Priming: Implications for In-Context Learning
    Zhenghao Herbert Zhou, Robert Frank, and R. Thomas McCoy
    Talk presented at the Student Session of the 35th European Summer School in Logic, Language and Information (ESSLLI), Leuven, Belgium, Aug 2024
    PDF

2023

  1. SCiL
    Simulating Structural Priming Effect with PIPS: Parallelism in Producing Syntax
    Zhenghao Herbert Zhou, and Robert Frank
    Talk presented at the Society for Computation in Linguistics 2023 (SCiL), Amherst, PA, Jun 2023
    Slides
  2. SCiL
    Subject-verb agreement with Seq2Seq transformers: Bigger is better, but still not best
    Michael Wilson, Zhenghao Zhou, and Robert Frank
    Poster presented at the Society for Computation in Linguistics 2023 (SCiL), Amherst, PA, Jun 2023
    Poster