❯ Guillaume Laforge

Things you never dared to ask about LLMs — Take 2

generative-ai large-language-models

Recently, I had the chance to deliver this talk on the mysteries of LLMs, at Devoxx France, with my good friend Didier Girard, It was fun to uncover the oddities of LLMs, and better understand where they thrive or fail, and why.

In this post, I’d like to share an update of the presentation deck, with a few additional slides here and there, to cover for example

  • the difficulty of LLMs to work with acronyms, scientific molecule names, plant names, special uncommon vocabulary, which require more tokens and weakens attention,
  • the difference between deterministic and probabilistic problems, and why predictive models are still important,
  • some limits of LLMs with regards to understanding dates, data ownership, or the fact they can’t easily forget what they learned.

This was fun delivering the talk with Didier, as a friendly dialogue makes things more entertaining! We were lucky that this talk was recorded (however, in French 🇫🇷) and you can watch the video below:

NOTE: if the video is not properly embedded above, please follow this direct link on YouTube.