Prompt like:

Extract the company names from the texts below and return as an array

– [“Google”, “Meta”, “Microsoft”]

  • BrainSlugs83@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Why do you need an LLM for this? Just use any NER model. It will be blazing fast and run locally.

    • LPN64@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Because let’s say you train your bert model to do this, you’ll have a specific limited class trained on a specific type of document.

      It will work on wikipedia articles but not on transcripts from your local police station.

      Using a llm will allow it to inherit from the wide knowledge of the llm.