↓ Skip to main content

Team seminars

Towards Understanding, Interpreting, and Using Language Models

Speaker
Maxime Peyrard (LIG, UGA)
Date
Room
Salle 306, bâtiment IMAG + visio

As a new GetAlp member, I’ll use this presentation to provide a shallow but broad overview of my recent research interests: (i) causal machine learning, a sub-field of ML aiming to understand and rectify issues arising from traditional statistical approaches; (ii) LLM interpretability, which I will argue should be rooted in causal reasoning, the rigorous framework to answer “why” questions; (iii) introducing Thought-Decoding, an emerging paradigm viewing LLMs as producers of semantically meaningful messages (thoughts), where the goal is to use LLMs in interactions with other AI systems, tools, or humans in control flows to iteratively refine and improve the thoughts until a robust answer is found.