Maxime Peyrard

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
Dec 10, 2023	Release of the aiFlows library to assemble flows of collaborative AI, tools, humans 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

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia

Giovanni Monea, Maxime Peyrard, Martin Josifoski, and 6 more authors

2023

arXiv Bib PDF

@article{monea2023glitch,
  title = {A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia},
  author = {Monea, Giovanni and Peyrard, Maxime and Josifoski, Martin and Chaudhary, Vishrav and Eisner, Jason and Kıcıman, Emre and Palangi, Hamid and Patra, Barun and West, Robert},
  year = {2023},
  eprint = {2312.02073},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
}

Flows: Building Blocks of Reasoning and Collaborating AI

Martin Josifoski, Lars Klein, Maxime Peyrard, and 7 more authors

2023

arXiv Bib PDF Code

@article{josifoski2023flows,
  title = {Flows: Building Blocks of Reasoning and Collaborating AI},
  author = {Josifoski, Martin and Klein, Lars and Peyrard, Maxime and Li, Yifei and Geng, Saibo and Schnitzler, Julian Paul and Yao, Yuxing and Wei, Jiheng and Paul, Debjit and West, Robert},
  year = {2023},
  eprint = {2308.01285},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
}

REFINER: Reasoning Feedback on Intermediate Representations

Debjit Paul, Mete Ismayilzada, Maxime Peyrard, and 4 more authors

2023

arXiv Bib PDF Code

@misc{paul2023refiner,
  title = {REFINER: Reasoning Feedback on Intermediate Representations},
  author = {Paul, Debjit and Ismayilzada, Mete and Peyrard, Maxime and Borges, Beatriz and Bosselut, Antoine and West, Robert and Faltings, Boi},
  eprint = {2304.01904},
  journal = {arXiv preprint arXiv:2304.01904},
  url = {https://arxiv.org/pdf/2304.01904.pdf},
  year = {2023},
}