Andreas Opedal

prof_pic.jpg
andreas.opedal@inf.ethz.ch

I am a PhD student at ETH Zurich, advised by Mrinmaya Sachan, Ryan Cotterell, and Bernhard Schölkopf, and supported by the Max Planck ETH Center for Learning Systems. I work on natural language processing, machine learning, and computational linguistics.

I am particularly interested in understanding the mechanisms behind language processing and reasoning, both in language models (interpretability) and in the human mind (cognitive modeling).

Prior to my doctoral studies, I obtained an MSc in Data Science from ETH Zurich and a BSc in Industrial Engineering from Chalmers University of Technology. I have also attended the University of California, Berkeley.

I am always open to new collaborations on projects that interest me. Please do reach out!

selected publications

  1. Preprint
    MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
    Andreas Opedal*, Haruki Shirakami*, Bernhard Schölkopf, Abulhair Saparov, and Mrinmaya Sachan
    2024
  2. EMNLP
    On the Role of Context in Reading Time Prediction
    Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, and Ethan Wilcox
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024
  3. ICML
    Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
    Andreas Opedal*, Alessandro Stolfo*, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, and Mrinmaya Sachan
    In Forty-first International Conference on Machine Learning, Jul 2024
  4. EMNLP
    An Exploration of Left-Corner Transformations
    Andreas Opedal*, Eleftheria Tsipidi*, Tiago Pimentel, Ryan Cotterell, and Tim Vieira
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023
  5. ACL
    Efficient Semiring-Weighted Earley Parsing
    Andreas Opedal, Ran Zmigrod, Tim Vieira, Ryan Cotterell, and Jason Eisner
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023