Maxime Peyrard

prof_pic.jpg

Welcome!

I am a junior Professor at the LIG in Grenoble, affiliated with the NLP team GetAlp. Previously, I was a Postdoctoral Scholar at EPFL, under the guidance of Robert West in the Data Science Lab. In 2019, I earned my Ph.D. in Computer Science from the UKP lab at TU Darmstadt, advised by Iryna Gurevych.

In my research, I am interested in understanding and overcoming challenges arising from the prevailing statistical perspective in NLP systems development. Going beyond statistical boundaries requires adopting a causal perspective. Equipped with the tools of causality, we can effectively tackle issues like out-of-distribution generalization, biases in pre-trained models, and extract mechanistic interpretations of the complex behavior of these models.

news

Jan 22, 2024 Our paper about evaluating large language model accepted at ICLR :fire: :tada:
Dec 10, 2023 Release of the aiFlows library to assemble flows of collaborative AI, tools, humans :boom: Join the discord, give feedback, and contribute
Dec 4, 2023 Our work studying how language model integrates in-context information using causal tracing analysis is out on arxiv. Code coming soon…

selected publications

  1. monea2023glitch_preview.png
    A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
    Giovanni Monea, Maxime Peyrard, Martin Josifoski, and 6 more authors
    2023
  2. aiflows_preview.png
    Flows: Building Blocks of Reasoning and Collaborating AI
    Martin Josifoski, Lars Klein, Maxime Peyrard, and 7 more authors
    2023
  3. refiner_preview.png
    REFINER: Reasoning Feedback on Intermediate Representations
    Debjit Paul, Mete Ismayilzada, Maxime Peyrard, and 4 more authors
    2023