LLM-generated labels for topic classification
6 min readMar 17, 2024
Read it first on my Substack
In a recent post, I trained a model to classify news articles by topic using just their URLs as input features. This approach, I argued, demonstrated the power of a lightweight dataset, provided the signal in the data was strong enough.
But even with this kind of model, there’s a limit to how lightweight the data can be. It still…