Presenting the Results of the Project “Infrastructure for Fine-Tuning Pre-trained Large Language Models”

logo

29 May 2026, 11:00 a.m.
Shared Workspace Hall, 16 Gen. Gurko Street, 6th Floor

On 29 May 2026, at 11:00 a.m., the results of the research project “Infrastructure for Fine-Tuning Pre-trained Large Language Models” will be presented at the Shared Workspace Hall, located at 16 Gen. Gurko Street, 6th Floor. The event is organized by the Department of Computational Linguistics at the Institute for Bulgarian Language “Prof. Lyubomir Andreychin”, Bulgarian Academy of Sciences.

The project aims to develop an open-access infrastructure consisting of algorithms and software tools for the selection and preprocessing of large-scale Bulgarian language datasets, as well as company- or industry-specific data. The infrastructure enables the fine-tuning of suitable open-source large language models for the solution of domain-specific and task-oriented applications.

Programme

Svetla Koeva

Presentation of the project “Infrastructure for Fine-Tuning Pre-trained Large Language Models”

Ivelina Stoyanova
The IfGPT Large-Scale Language Dataset: Metadata Management and Data Quality Assurance
Yordan Kralev
Infrastructure for Building Chatbots with Large Language Models and Context-Augmented Instruction Processing
Valentina Stefanova
Bulgarian Language Datasets for the Evaluation of Large Language Models
Scroll to Top