• obbeel
    link
    fedilink
    arrow-up
    1
    ·
    12 days ago

    Maybe we just need a different type of NLP to work with summarization. I have noticed before LLMs are unlikely to escape their ‘base’ knowledge.

    • ☆ Yσɠƚԋσʂ ☆@lemmy.mlOP
      link
      fedilink
      arrow-up
      2
      ·
      12 days ago

      That’s very likely the case. LLMs sucking up all the air in ML research right now, and we shouldn’t be using them as a hammer for every problem.