Large Language Models

The article addresses the problem of text classification in the context of growing information flows and the need for automated content analysis. A universal information technology is proposed, combining classical machine learning methods with the potential of Large Language Models for processing news, scientific, literary, journalistic and legal texts. Using the BBC News corpus (2225 texts), k-means clustering with TF-IDF demonstrated clear thematic grouping.

This paper presents Small Synthetic Embedding Dataset, a fully synthetic dataset in Ukrainian designed for training, fine-tuning, and evaluating text embedding models. The use of large language models (LLMs) allows for controlling the diversity of generated data in aspects such as NLP tasks, asymmetry between queries and documents, the presence of instructions, support for various languages, and avoidance of social biases. A zero-shot generation approach was used to create a set of Ukrainian query-documents pairs with corresponding similarity scores.

The work is dedicated to the study of large language models (LLMs) and approaches to improving their efficiency in a new service. The rapid development of LLMs based on transformer architecture has opened up new possibilities in natural language processing and the automation of various tasks. However, fully utilizing the potential of these models requires a thorough approach and consideration of numerous factors.

The work is dedicated to the study of fundamental prompting techniques to improve the efficiency of using large language models (LLMs). Significant attention is given to the issue of prompt engineering. Various techniques are examined in detail: zero-shot prompting, feedback prompting, few-shot prompting, chain-of-thought, tree of thoughts, and instruction tuning. Special emphasis is placed on Reaction & Act Prompting and Retrieval Augmented Generation (RAG) as critical factors in ensuring effective interaction with LLMs.