Style Vectors For Steering Generative Large Language Model
Konen Kai, Jentzsch Sophie, Diallo Diaoulé, Schütt Peer, Bensch Oliver, Baff Roxanne El, Opitz Dominik, Hecking Tobias. Arxiv 2024
[Paper]
This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text generation. We show that style vectors can be simply computed from recorded layer activations for input texts in a specific style in contrast to more complex training-based approaches. Through a series of experiments, we demonstrate the effectiveness of activation engineering using such style vectors to influence the style of generated text in a nuanced and parameterisable way, distinguishing it from prompt engineering. The presented research constitutes a significant step towards developing more adaptive and effective AI-empowered interactive systems.
Similar Work