Comment on Researchers have found the cause of hallucinations in LLMs, H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs

so_pitted_wabam@lemmy.zip ⁨1⁩ ⁨day⁩ ago

• Skullgrid@lemmy.world ⁨1⁩ ⁨day⁩ ago

  This article is like reading the headline “Researchers have identified the cause of AIDS” and then you open it up and the body is a bunch of science jargon that basically says HIV.

  Concerning their origins, we trace these neurons back to the pre-trained base models and find that these neurons remain predictive for hallucination detection, indicating they emerge during pre-training.

  it sounds like it’s just how the systems are designed.

  I mean, the point of this shit is to take training data and create new stuff out of it through pattern matching. You’re going to get some mismatched shit by design,since the random decisions are modified by the weights. Otherwise you’d get the same shit every time.

  source

  • snooggums@piefed.world ⁨1⁩ ⁨day⁩ ago

    When the system is intended to look like a random a person then randomness is fine.

    When the output is expected to be accurate, it should be the same each time so it can be verified as accurate.

    LLMs are being sold as doing both at the same time, but random plus consistent equals random.

    source

    • Skullgrid@lemmy.world ⁨1⁩ ⁨day⁩ ago

      throw it onto the pile of people being idiots

      source

      • XLE@piefed.social ⁨1⁩ ⁨day⁩ ago

        throw it onto the pile of people being idiots AI companies lying to the public

        source
  • XLE@piefed.social ⁨1⁩ ⁨day⁩ ago

    That’s incorrect. Wrong responses will still be generated even if you remove the element that randomizes the response for the same question.

    If that wasn’t the case, this paper wouldn’t exist.

    source