Tootfinder

Neologism Learning for Controllability and Self-Verbalization
John Hewitt, Oyvind Tafjord, Robert Geirhos, Been Kim
https://arxiv.org/abs/2510.08506 https://

Neologism Learning for Controllability and Self-Verbalization
Humans invent new words when there is a rising demand for a new useful concept (e.g., doomscrolling). We explore and validate a similar idea in our communication with LLMs: introducing new words to better understand and control the models, expanding on the recently introduced neologism learning. This method introduces a new word by adding a new word embedding and training with examples that exhibit the concept with no other changes in model parameters. We show that adding a new word allows for …

I'm not opposed to neologisms. To the contrary, I do love them, sometimes coining my own or adapting happily. That is, as long as they make the language richer, or perhaps more precise.
What I truly hate is the modern goo that people are speaking, because they don't know their own language well. The business newspeak, so to say.
This is especially bad in Polish where people are randomly polonizing English words for no reason at all.