I want to fine tune an LLM to “steer” it in the right direction. I have plenty of training examples in which I stop the generation early and correct the output to go in the right direction, and then resume generation.

Basically, for my dataset doing 100 “steers” on a single task is much cheaper than having to correct 100 full generations completely, and I think each of these “steer” operations has value and could be used for training.

So maybe I’m looking for some kind of localized DPO. Does anyone know if something like this exists?

  • iii@mander.xyz
    link
    fedilink
    English
    arrow-up
    2
    ·
    2 days ago

    So supervised vs unsupervised, according to you, is a property of the dataset?

    • hok@lemmy.dbzer0.comOP
      link
      fedilink
      English
      arrow-up
      1
      arrow-down
      1
      ·
      2 days ago

      Sorry, I really don’t care to continue talking about the difference between supervised and unsupervised learning. It’s a pattern used to describe how you are doing ML. It’s not a property of a dataset (you wouldn’t call Dataset A “unsupervised”). Read the Wikipedia articles for more details.