1 Matching Annotations
  1. Oct 2023
  2. arxiv.org arxiv.org
    2305.15486.pdf
    1
    1. mark.crowley 25 Oct 2023
      Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RLbaselines, trained for 1M steps, without any training.

      Them's fighten' words!

      I haven't read it yet, but we're putting it on the list for this fall's reading group. Seriously, a strong result with a very strong implied claim. they are careful to say it's from their empirical results, very worth a look. I suspect that amount of implicit knowledge in the papers, text and DAG are helping to do this.

      The Big Question: is their comparison to RL baselines fair, are they being trained from scratch? What does a fair comparison of any from-scratch model (RL or supervised) mean when compared to an LLM approach (or any approach using a foundation model), when that model is not really from scratch.

      reinforcement-learning rdgrp-f23 reading_group_crowley nlp larg deep-learning self-supervised supervised-learning evaluation-methods
    Visit annotations in context

    Tags

    Annotators

    URL

    arxiv.org/pdf/2305.15486.pdf