paper-with-me

Papers

Styles + Persona-plug = Customized LLMs

2026-01-10 · Yutong Song, Jiang Wu, Shaofan Yuan, Chengze Shen, Jian Wang, Amir Rahmani, Nikil Dutt, Yu Wang arxiv

We discover a previously overlooked challenge in personalized text generation: personalization methods are increasingly applied under explicit style instructions, yet their behavior under such constraints remains poorly understood. To balance implicit personalization and explicit style, we formulate personalization as a distributional residual and propose PsPLUG, a lightweight soft-prompt plug-in trained with style-conditioned preference contrasts. Across LaMP benchmark, our framework improves persona alignment, maintains stylistic fidelity, and outperforms retrieval-based and soft-prompt baselines with minimal computation. These results show that residual modeling provides a simple and principled foundation for controllable, style-aware LLM personalization.

📄 PDF Abstract BibTeX arXiv:2601.06362

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

LLMs + Persona-Plug = Personalized LLMs

2024-09-18 · Jiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei 외

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of…

Language Modelling

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

2023-01-01 · CVPR 2023 1 · Haoming Lu, Hazarapet Tunanyan, Kai Wang, Shant Navasardyan 외

Diffusion models have demonstrated impressive capability of text-conditioned image synthesis, and broader application horizons are emerging by personalizing those pretrained diffusion models toward generating some sp…

DisentanglementImage Generation

SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization

2025-02-27 · Shubhankar Borse, Kartikeya Bhardwaj, Mohammad Reza Karimi Dastjerdi, Hyojin Park 외

Diffusion models are increasingly popular for generative tasks, including personalized composition of subjects and styles. While diffusion models can generate user-specified subjects performing text-guided actions in cus…

Denoising

Prompt2Fashion: An automatically generated fashion dataset

2024-09-10 · Georgia Argyrou, Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos 외

Despite the rapid evolution and increasing efficacy of language and vision generative models, there remains a lack of comprehensive datasets that bridge the gap between personalized fashion needs and AI-driven design, li…

Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors

2025-09-18 · Zhengxiang Wang, Nafis Irtiza Tripto, Solha Park, Zhenzhen Li 외 arxiv

As large language models (LLMs) become increasingly integrated into personal writing tools, a critical question arises: can LLMs faithfully imitate an individual's writing style from just a few examples? Personal style i…