paper-with-me

Papers

Style Vectors for Steering Generative Large Language Model

2024-02-02 · Kai Konen, Sophie Jentzsch, Diaoulé Diallo, Peer Schütt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, Tobias Hecking

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.

📄 PDF Abstract BibTeX arXiv:2402.01618

Code (1)

dlr-sc/style-vectors-for-steering-llms 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language ModelPrompt EngineeringText Generation

Similar Papers 제목 키워드 기반

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer

2025-12-22 · Raina Panda, Daniel Fein, Arpita Singhal, Mark Fiore 외 arxiv

Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt engineering, all of which can be computat…

Prompt EngineeringStyle Transfer

Generative Modeling of Individual Behavior at Scale

2025-02-20 · Nabil Omi, Lucas Caccia, Anurag Sarkar, Jordan T. Ash 외

There has been a growing interest in using AI to model human behavior, particularly in domains where humans interact with this technology. While most existing work models human behavior at an aggregate level, our goal is…

Image GenerationMulti-Task Learningparameter-efficient fine-tuning

On the Limits of Steering Vectors for Preference-Aligned Generation

2026-07-02 · Melanie Subbiah, Zara Hall, Kathleen McKeown arxiv

Steering vectors have emerged as a promising approach to controlled text generation, offering interpretable, training-free mechanisms for shaping model outputs. However, their practical generality remains poorly understo…

Text Generation

Can sparse autoencoders be used to decompose and interpret steering vectors?

2024-11-13 · Harry Mayne, Yushi Yang, Adam Mahdi

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to…

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations

2025-05-16 · Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural act…