Personalized Text Generation with Contrastive Activation Steering

• URL: http://arxiv.org/abs/2503.05213v1
• Date: Fri, 07 Mar 2025 08:07:15 GMT
• Title: Personalized Text Generation with Contrastive Activation Steering
• Authors: Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, Tat-Seng Chua,
• Abstract summary: We propose a training-free framework that disentangles and represents personalized writing style as a vector.<n>Our framework achieves a significant 8% relative improvement in personalized generation while reducing storage requirements by 1700 times over PEFT method.
• Score: 63.60368120937822
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two paradigms: retrieval-augmented generation (RAG) and parameter-efficient fine-tuning (PEFT). While these approaches have advanced the field, they suffer from two critical limitations: (1) the entanglement of content semantics and stylistic patterns in historical texts impedes accurate modeling of user-specific writing preferences; and (2) scalability challenges arising from both RAG's inference latency by retrieval operations and PEFT's parameter storage requirements for per user model. To overcome these limitations, we propose StyleVector, a training-free framework that disentangles and represents personalized writing style as a vector in LLM's activation space, enabling style-steered generation during inference without requiring costly retrieval or parameter storage. Comprehensive experiments demonstrate that our framework achieves a significant 8% relative improvement in personalized generation while reducing storage requirements by 1700 times over PEFT method.

Related papers

• Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing [53.295515505026096]
  Janus-Pro-driven Prompt Parsing is a prompt- parsing module that bridges text understanding and layout generation. MIGLoRA is a parameter-efficient plug-in integrating Low-Rank Adaptation into UNet (SD1.5) and DiT (SD3) backbones. The proposed method achieves state-of-the-art performance on COCO and LVIS benchmarks while maintaining parameter efficiency.
  arXiv  Detail & Related papers  (2025-03-27T00:59:14Z)
• Training Sparse Mixture Of Experts Text Embedding Models [0.0]
  Transformer-based text embedding models have improved their performance on benchmarks like MIRACL and BEIR by increasing their parameter counts.<n>This scaling approach introduces significant deployment challenges, including increased inference latency and memory usage.<n>We introduce Nomic Embed v2, the first general purpose MoE text embedding model.
  arXiv  Detail & Related papers  (2025-02-11T21:36:31Z)
• Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>We introduce novel methodologies and datasets to overcome these challenges.<n>We propose MhBART, an encoder-decoder model designed to emulate human writing style.<n>We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• Refining Joint Text and Source Code Embeddings for Retrieval Task with Parameter-Efficient Fine-Tuning [0.0]
  We propose a fine-tuning frame-work that leverages. Efficient Fine-Tuning (PEFT) techniques. We demonstrate that the proposed fine-tuning framework has the potential to improve code-text retrieval performance by tuning only 0.4% parameters at most.
  arXiv  Detail & Related papers  (2024-05-07T08:50:25Z)
• Successor Features for Efficient Multisubject Controlled Text Generation [48.37713738712319]
  We introduce SF-GEN, which is grounded in two primary concepts: successor features (SFs) and language model rectification. SF-GEN seamlessly integrates the two to enable dynamic steering of text generation with no need to alter the LLM's parameters. To the best of our knowledge, our research represents the first application of successor features in text generation.
  arXiv  Detail & Related papers  (2023-11-03T00:17:08Z)
• Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control [15.881568820009797]
  We introduce a novel text generation task called Precise Outline-conditioned Generation. This task requires generating stories based on specific, sentence-level outlines. We propose an explicit outline utilization control approach and a novel framework that leverages the task duality between summarization and generation.
  arXiv  Detail & Related papers  (2023-05-23T18:33:52Z)
• Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain [53.22419717434372]
  We propose a new task, namely stylized data-to-text generation, whose aim is to generate coherent text according to a specific style. This task is non-trivial, due to three challenges: the logic of the generated text, unstructured style reference, and biased training samples. We propose a novel stylized data-to-text generation model, named StyleD2T, comprising three components: logic planning-enhanced data embedding, mask-based style embedding, and unbiased stylized text generation.
  arXiv  Detail & Related papers  (2023-05-05T03:02:41Z)
• Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters [66.17039929803933]
  We propose a novel transfer learning framework which updates only $0.3%$ of model parameters to learn style specific attributes for response generation. We learn style specific attributes from the PERSONALITY-CAPTIONS dataset.
  arXiv  Detail & Related papers  (2022-10-07T00:09:22Z)
• COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics [69.8062252611486]
  Cold decoding is a flexible framework that can be applied directly to off-the-shelf left-to-right language models. Our experiments on constrained generation tasks point to the effectiveness of our approach, both in terms of automatic and human evaluation.
  arXiv  Detail & Related papers  (2022-02-23T18:59:27Z)
• Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning [8.142947808507367]
  Paraphrase generation is a fundamental and long-standing task in natural language processing. We propose Retrieval Augmented Prompt Tuning (RAPT) as a parameter-efficient method to adapt large pre-trained language models for paraphrase generation. We also propose Novelty Conditioned RAPT (NC-RAPT) as a simple model-agnostic method of using specialized prompt tokens for controlled paraphrase generation.
  arXiv  Detail & Related papers  (2022-02-01T16:26:36Z)

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.