Wowed by a new paper I just read and wish I had thought to write myself. Lukas Berglund and others, led by Owain Evans, asked a simple, powerful, elegant question: can LLMs trained on A is B infer automatically that B is A? The shocking (yet, in historical context, see below, unsurprising) answer is no:
  • Spzi@lemm.eeEnglish
    5·
    1 year ago

    What this is about:

    Can LLMs trained on A is B infer automatically that B is A?

    Models that have memorized “Tom Cruise’s parent is Mary Lee Pfeiffer” in training, fail to generalize to the question “Who is Mary Lee Pfeiffer the parent of?”. But if the memorized fact is included in the prompt, models succeed.

    It’s nice that it can get the latter, matching a template, but problematic that they can’t take an abstraction that they superficially get in one context and generalize it another; you shouldn’t have to ask it that way to get the answer you need.