- Published on
LLMs and Reasoning
- Authors
- Name
- Martin Andrews
- @mdda123
Presentation Link
Sam Witteveen and I started the Machine Learning Singapore Group (or MLSG for short) on MeetUp in February 2017 (it was previously named "TensorFlow and Deep Learning Singapore"), and the forty-sixth MeetUp was our tenth 'in-person' event since the COVID era.
My talk covered "Large Language Models and Reasoning":
- Can current LLMs can actually do reasoning - or is it an illusion?
- Some methods through which 'genuine reasoning' is being attempted:
- Self-critique; Create outlines; Write code / DSLs; Verification; Game-play
- (potentially...) a demo of the PAL method in Flowise
Sam talked about fine-tuning Google's PaLM using Vertex AI, including demonstrations with Emoji-Stories and Singlish-ifying a chatbot.
We also were pleased to have Florian Kowarsch giving a talk about the role of explainable AI (XAI) in Cancer cell classification - and how these methods can actually feed back into making systems more robust and useful.
Many thanks to the Google team, who not only allowed us to use Google's Developer Space, and put out the extra chairs required for our larger-than-expected attendence, but were also kind enough to provide Pizza for the attendees!
The slides for my talk, which contain links to all of the reference materials and sources, are here :
If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.
