According to which philologist? In short: they are both weak terms, 'hallucination' and 'confabulation', and we are using them in this context very loosely (and it should be in the open).
About the terms themselves, "confabulate" means "exchanging stories", while "hallucinate" is less clear but probably means "to err". In psychiatry, "hallucinate" was apparently introduced by Esquirol and "confabulate" by Wernicke and Bonhoeffer; neither concept seems to be akin to the substance of the phenomenon of "stochastic parrots bullshitting an unchecked narrative through formal plausibility".
Let's ask chatgpt free (coz I'm cheap) what it not-thinks about these, and ask for more statistically generated bullshit:
-- 8< --
These are some creative and fun suggestions! Here's my take:
Digimagination: This one has a sleek, almost sci-fi ring to it. It captures the digital, machine-driven nature of language model "hallucination," but presents it in a positive, imaginative light. This could highlight the creative aspect of AI responses, even when they aren't grounded in fact.
Stochafubalation: Combining "stochastic" (random probability) with "confabulation" is clever. It emphasizes the statistical nature of language models making up facts, though it could be a bit of a mouthful.
Statillucination: I like how this merges "statistical" and "hallucination." It feels technical and would fit right into the AI research community's vocabulary.
Matmulshitting: This one is tongue-in-cheek and hilarious! It references matrix multiplication (which drives many neural network operations) with a humorous, blunt twist. Probably not for formal use, but great for informal contexts!
Here are a few more neologisms I can propose:
Probafabrication: A combination of "probability" and "fabrication," highlighting the statistical underpinnings of how LLMs generate falsehoods.
Algoillusion: A fusion of "algorithm" and "illusion," suggesting the misleading or illusionary nature of generated information.
Synthifalse: A contraction of "synthetic" and "false," pointing to AI-generated responses that are not grounded in reality.
Pseudoformulation: Emphasizing that the response is a pseudo (false) formulation rather than a real answer.
Modelucination: A blend of "model" and "hallucination," capturing the fact that the machine learning model is generating false or misleading data.
My judgement of yours: I love 'stochfabulating' and 'matmulshitting', but I condemn 'digimagining'. Digimagining is doable in proper terms (no pun intended).
"Pretending" is too human to my taste: it assumes the thing doing the pretend thing knows about the real thing. It's something kids do during play. I'm too afraid of the consequences to admit LLMs are anywhere near this situation wink
About the terms themselves, "confabulate" means "exchanging stories", while "hallucinate" is less clear but probably means "to err". In psychiatry, "hallucinate" was apparently introduced by Esquirol and "confabulate" by Wernicke and Bonhoeffer; neither concept seems to be akin to the substance of the phenomenon of "stochastic parrots bullshitting an unchecked narrative through formal plausibility".
See: "Hallucinations and related concepts - their conceptual background" - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4515540/
and: "The Confabulating Mind: How the Brain Creates Reality" - https://psychiatryonline.org/doi/full/10.1176/appi.ajp.2008....