Confidence in Classification using LLMs and Conformal Sets

One of the common use cases for large language models is classifying text -- but data scientists often want to know the confidence that the text falls into the category. This blog post shows an example using a models log-probabilities to determine if text has obscene language, while setting the recall rate or estimating the precision of the classification.

Continue reading...

Getting Updates

If you wish to get updates from the CRIME De-Coder, use the RSS feed to get updates in Outlook or a feed reader (like Inoreader). Or use a service like IFTTT to sign up for email alerts when CRIME De-Coder posts new content (via the RSS feed to email app).

Archives