Style Vectors for Steering Generative Large Language Model

• URL: http://arxiv.org/abs/2402.01618v1
• Date: Fri, 2 Feb 2024 18:31:15 GMT
• Title: Style Vectors for Steering Generative Large Language Model
• Authors: Kai Konen, Sophie Jentzsch, Diaoul\'e Diallo, Peer Sch\"utt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, Tobias Hecking
• Abstract summary: We show that style vectors can be computed from recorded layer activations for input texts in a specific style. The presented research constitutes a significant step towards developing more adaptive and effective AI-empowered interactive systems.
• Score: 1.4815455267254962
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Style-Specific Neurons for Steering LLMs in Text Style Transfer [55.06697862691798]
  Text style transfer (TST) aims to modify the style of a text without altering its original meaning. We present sNeuron-TST, a novel approach for steering large language models using style-specific neurons.
  arXiv  Detail & Related papers  (2024-10-01T11:25:36Z)
• StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models [35.732715025002705]
  StyleInject is a specialized fine-tuning approach tailored for text-to-image models. It adapts to varying styles by adjusting the variance of visual features based on the characteristics of the input signal. It proves particularly effective in learning from and enhancing a range of advanced, community-fine-tuned generative models.
  arXiv  Detail & Related papers  (2024-01-25T04:53:03Z)
• GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents [3.229105662984031]
  GestureDiffuCLIP is a neural network framework for synthesizing realistic, stylized co-speech gestures with flexible style control. Our system learns a latent diffusion model to generate high-quality gestures and infuses the CLIP representations of style into the generator. Our system can be extended to allow fine-grained style control of individual body parts.
  arXiv  Detail & Related papers  (2023-03-26T03:35:46Z)
• StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model [64.26721402514957]
  We propose StylerDALLE, a style transfer method that uses natural language to describe abstract art styles. Specifically, we formulate the language-guided style transfer task as a non-autoregressive token sequence translation. To incorporate style information, we propose a Reinforcement Learning strategy with CLIP-based language supervision.
  arXiv  Detail & Related papers  (2023-03-16T12:44:44Z)
• Composable Text Controls in Latent Space with ODEs [97.12426987887021]
  This paper proposes a new efficient approach for composable text operations in the compact latent space of text. By connecting pretrained LMs to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. Experiments show that composing those operators within our approach manages to generate or edit high-quality text.
  arXiv  Detail & Related papers  (2022-08-01T06:51:45Z)
• StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery [71.1862388442953]
  We develop a text-based interface for StyleGAN image manipulation. We first introduce an optimization scheme that utilizes a CLIP-based loss to modify an input latent vector in response to a user-provided text prompt. Next, we describe a latent mapper that infers a text-guided latent manipulation step for a given input image, allowing faster and more stable text-based manipulation.
  arXiv  Detail & Related papers  (2021-03-31T17:51:25Z)
• On Learning Text Style Transfer with Direct Rewards [101.97136885111037]
  Lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. We leverage semantic similarity metrics originally used for fine-tuning neural machine translation models. Our model provides significant gains in both automatic and human evaluation over strong baselines.
  arXiv  Detail & Related papers  (2020-10-24T04:30:02Z)
• Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory [65.98002918470543]
  We introduce a new prototype-to-style framework to tackle the challenge of stylistic dialogue generation. The framework uses an Information Retrieval (IR) system and extracts a response prototype from the retrieved response. A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response.
  arXiv  Detail & Related papers  (2020-04-05T14:36:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.