Comment by dinobones

Dunno if this passes the bootstrapping test.

This is sensitive to the initial candidate set of labels that the LLM generates.

Meaning if you ran this a few times over the same corpus, you’ll probably get different performance depending upon the order of the way you input the data and the classification tag the LLM ultimately decided upon.

Here’s an idea that is order invariant: embed first, take samples from clusters, and ask the LLM to label the 5 or so samples you’ve taken. The clusters are serving as soft candidate labels and the LLM turns them into actual interpretable explicit labels.