Matthew Finlayson

mattbnfin at gmail dot com


I am a PhD student at USC, advised by Swabha Swayamdipta and Xiang Ren. Previously, I was a Predoctoral Researcher at AI2, and before that I studied computer science and linguistics at Harvard.

My current research focuses on improving language modeling, sampling, and interpretability methods by building and exploiting our theoretical understanding of neural language models.


Gave at talk at Meta FAIR on stealing ChatGPT's hidden size.
Gave at talk at CMU LTI on decoding and the softmax bottleneck.
Paper accepted to ICLR 2024.
Paper accepted to EMNLP.
Joined USC as a PhD student in NLP.
Selected for NSF GRFP Honorable Mention.
Gave a talk at IST/Unbabel on math reasoning evaluation.
More news
Decomposed Prompting accepted to ICLR.
Gave a talk at FLaNN on studying instruction learning with formal languages.
2 papers accepted to EMNLP.
Joined AI2 as a pre-doctoral researcher.



Publications and preprints

  1. Logits of API-Protected LLMs Leak Proprietary Information.
    Matthew Finlayson, Xiang Ren, and Swabha Swayamdipta.
    ArXiv, .
  2. Closing the Curious Case of Neural Text Degeneration.
    Matthew Finlayson, John Hewitt, Alexander Koller, Swabha Swayamdipta, and Ashish Swbharwal.
    ICLR, .
  3. Attentiveness to Answer Choices Doesn't Always Entail High QA Accuracy.
    Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord, Peter Clark, and Ashish Sabharwal.
    EMNLP, .
  4. Decomposed Prompting: A Modular Approach for Solving Complex Tasks.
    Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark and Ashish Sabharwal.
    ICLR, .
    [PDF] [Code]
  5. Līla: A Unified Benchmark for Mathematical Reasoning.
    {Matthew Finlayson, Swaroop Mishra,} Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, and Ashwin Kalyan.
    EMNLP, .
    [PDF] [Data] [Model] [Website] [Leaderboard]
  6. What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment.
    Matthew Finlayson, Kyle Richardon, Ashish Sabharwal, and Peter Clark.
    EMNLP, .
    [PDF] [Code]
  7. Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models.
    {Matthew Finlayson, Aaron Mueller,} Sebastian Gehrmann, Stuart Shieber, Tal Linzen, and Yonatan Belinkov.
    ACL, .
    [PDF] [Code]