[enragedcacti]

They are stochastic in the domain of meaning. Minor syntactic changes to the prompt or changes to the seed can result in substantial* changes to the meaning of the response.

*substantial as in nontrivial, not substantial as in massive

[8note]

Isn't that rather "unstable" or "poorly conditioned" ?

[enragedcacti]

Sure, I don't think those are mutually exclusive with stochastic. A stable or well-conditioned model may just have an acceptably small standard deviation for the task at hand.

[seydor]

Similar prompts give similar continuations, not wildly diverging, so no

[enragedcacti]

By definition most continuations won't be wildly divergent under a stochastic model because its following a bell curve.

[seydor]

Stochasticty of meaning is not defined. I think it's an unfortunate use of the term

Humans are also like that

[enragedcacti]

Difficulty to define rigorously does not preclude its existence or usefulness as model. The paper addresses how it feels humans are different from LLMs in reference to meaning.

[seydor]

Still sounds like a nonsense term. What would be non-stochasticity of meaning?

[enragedcacti]

Reliably conferring the same mental model to another entity regardless of syntactic differences, or just failing to do so in a way that isn't predictable by a bell curve. The paper makes the argument that humans modelling the mental state of their conversation partner is part of how reliable meaning is exchanged, something that LLMs are unable to do because it is completely absent from their training data.