EUVIMEDEUVIMED entdecken
Crossref

Dialog style transfer with parameter-efficient fine-tuning

Ruslan Pravosud, Oleksandr Marchenko

Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics · 2025 · (2) · 193-196

DOI: 10.17721/1812-5409.2025/2.30 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics, 2025. Verfasst von Ruslan Pravosud und 1 weiteren Autor:innen. Die Arbeit nennt 8 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work explores the application of modern fine-tuning methods, characterized by high parameter efficiency, to the task of generating dialogue responses in the style of a specific fictional or real-life character. The main goal of the study is to develop an approach that allows existing language models to be adapted to the specific communication or speech style of a particular personality using a minimal number of new parameters. This avoids the need for full retraining of large models and reduces computational costs. One of the key objectives is to enable the implementation of a compact yet functional language model that can be run on a standalone computer without requiring servers or powerful graphics processors. Such an approach opens new possibilities for personalized or entertainment applications, such as creating chatbots capable of interacting with users in the persona of a character from a book, movie, or even a historical figure. To implement this approach, we propose the use of the LoRA (Low-Rank Adaptation) method, which allows efficient fine-tuning of existing transformer architectures — in particular, the GPT-2 model — without retraining all of its layers. Using LoRA makes it possible to add stylistic features to the model’s speech without compromising its core ability to generate logical and coherent texts. To evaluate how well the model has learned to imitate the target speech style, we additionally train a BERT model as a classifier to distinguish between texts written in the desired style and ordinary, neutral responses. This provides an objective quality metric for generation and allows us to assess the effectiveness of the fine-tuning. The dataset used for training was generated using the GPT-4 mini model, which enables the rapid creation of a large number of examples in the desired style.

Zitieren

APA

Pravosud, R., & Marchenko, O. (2025). Dialog style transfer with parameter-efficient fine-tuning. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics, 193-196. https://doi.org/10.17721/1812-5409.2025/2.30

Vancouver

Pravosud R, Marchenko O. Dialog style transfer with parameter-efficient fine-tuning. Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics. 2025:193-196. doi:10.17721/1812-5409.2025/2.30

BibTeX
@article{Pravosud2025,
  author = {Pravosud, Ruslan and Marchenko, Oleksandr},
  title = {Dialog style transfer with parameter-efficient fine-tuning},
  journal = {Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics},
  year = {2025},
  number = {2},
  pages = {193--196},
  doi = {10.17721/1812-5409.2025/2.30}
}
Kostenlos starten →