Saved in:
Bibliographic Details
Main Authors: Park, Sungjoon, Ramamurthi, Varun, Terry, Owen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.18551
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give me a neologism answer." Behavioral steering can also be achieved through fine-tuning, albeit with more compute and less flexibility: learning a neologism only trains d parameters and allows the user to still access the model's default behavior. We compare the performance of neologism learning against low-rank adaptation (LoRA) fine-tuning, finding that neologisms outperform fine-tuned models under a matched training setup (same data and hyperparameters). We also investigate self-verbalizations of neologisms, and observe that the model will occasionally make up its own new words when asked about a neologism.