‹ BackHN Continuity

Thread

LLM Classification Is Feature Engineering

116 points · 25 comments · minsufficient

  1. twelfthnight · · focus · HN ↗
    Why not use a text embedder for the unstructured data and concatenate with the structured data?

    For example you could freeze most of the layers of the embedder but let the final ones learn. Then you wouldn’t need to do either feature or prompt engineering?

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.