Hallucination or Invention?
The thin line between a model failing to recall facts and succeeding at generating novel concepts.
In the context of Large Language Models, a "hallucination" is defined as a confident response that is factually incorrect or unsupported by the prompt. However, from the perspective of the neural network, it is simply navigating the latent space based on its training distribution.
The Mechanism of Creativity
Human creativity often involves combining disparate ideas to form something new. When an LLM does this and produces a novel solution to a coding problem, we call it "zero-shot reasoning." When it does the exact same thing but produces a fake legal citation, we call it a "hallucination."
The algorithmic process behind invention and hallucination is identical. The only difference is whether the output aligns with our external, objective reality.
| Outcome | Process | Value |
|---|---|---|
| Fake Citation | Latent Space Interpolation | Negative (Deceptive) |
| Novel Metaphor | Latent Space Interpolation | Positive (Creative) |