Edge Analytics
Published in

Edge Analytics

Getting the Most Out of GPT-3-based Text Classifiers: Part Two

Fine-Tuning Prompts with Probability Spectrums

Photo by Markus Winkler on Unsplash

What is GPT-3?

In this example, the text in bold is the “prompt” and the rest of the text is GPT-3’s “prediction”.

Using Probability Spectrums Effectively

Label the tweets as either "positive", "negative", "mixed", or "neutral":
Tweet: I can say that there isn't anything I would change.
Label: positive
Tweet: I'm not sure about this.
Label: neutral
Tweet: I liked some parts but I didn't like other parts.
Label: mixed
Tweet: I think the background image could have been better.
Label: negative
Tweet: I liked it.
Label:
The “Show probability” option can be found in the bottom right corner of the playground.
GPT-3 considers the label “positive” to have a probability of 58%.
Here, GPT-3 considers the label “neutral” to be less probable at ~34%.

Summary

GPT-3 at Edge Analytics

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store