Controlled Text Generation via Language Model Arithmetic

arXiv:2311.14479v2 Announce Type: replace
Abstract: As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model arithmetic, a novel inference framework for composing and biasing LLMs without the need for model (re)training or highly specific datasets. In addition, the framework allows for more precise control of generated text than direct prompting and prior controlled text generation (CTG) techniques. Using model arithmetic, we can express prior …

arxiv controlled text generation cs.cl language language model text text generation type via