Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
In-Context Learning for Extreme Multi-Label Classification
Learn how large language models can classify over 10,000 labels with minimal data, using systematic prompt searching. This talk explores a Stanford paper and code for extreme multi-label classification.
How to leverage large language models to identify > 10,000 different labels with < 10 labelled examples for each class? And how to do it by systematically searching the prompt space without tinkering with prompts for each class?
There is this Stanford paper (From Chris Potts’ group) and an accompanying Github repository that offers an answer to the questions above.
I have been tinkering with it. The idea was to share what I am learning with fellow tinkerers in a quick talk.
dspy optimizes few-shot In-Context Learning for Extreme Multi-Label Classification (XMC).
Compose Email
Loading recent emails...