Bookmark Saya

arXiv Open Access 2024

GigaPevt: Multimodal Medical Assistant

Pavel Blinov Konstantin Egorov Ivan Sviridov Nikolay Ivanov Stepan Botman +4 lainnya
Lihat Sumber

Abstrak

Building an intelligent and efficient medical assistant is still a challenging AI problem. The major limitation comes from the data modality scarceness, which reduces comprehensive patient perception. This demo paper presents the GigaPevt, the first multimodal medical assistant that combines the dialog capabilities of large language models with specialized medical models. Such an approach shows immediate advantages in dialog quality and metric performance, with a 1.18% accuracy improvement in the question-answering task.

Topik & Kata Kunci

cs.AI cs.CL cs.HC

Penulis (9)

P

Pavel Blinov

K

Konstantin Egorov

I

Ivan Sviridov

N

Nikolay Ivanov

S

Stepan Botman

E

Evgeniy Tagin

S

Stepan Kudin

G

Galina Zubkova

A

Andrey Savchenko

Format Sitasi

APA MLA BibTeX
Blinov, P., Egorov, K., Sviridov, I., Ivanov, N., Botman, S., Tagin, E. et al. (2024). GigaPevt: Multimodal Medical Assistant. https://arxiv.org/abs/2402.16654

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓