Methodology of Using Large Language Models to Solve Tasks of State and Municipal Government for Intelligent Abstracting and Automatic Generation of Text Content

Large language models (LLM) are finding new areas of application in practice, including the sphere of public and municipal administration. To increase the efficiency of the practical application of large language models rules and methods of interaction with them are developed, taking into account the specifics, a wide range of their possible use and increasing accessibility. The article examines the issues of improving the efficiency of large language models with various types of content using prompt engineering techniques. An analysis of a significant number of prompts for large language models and methods for their formation is presented. The article discusses the possibilities of using large language models, trained (customizable) using creative prompting for intelligent abstracting of various content with the subsequent generation of original texts and text documents for the sphere of state and municipal administration. The proposed methodology makes it possible to effectively integrate knowledge from various sources

into LLM training and turn it into a truly intelligent tool that expands the possibilities of its work. When applying this approach, the LLM acts as a powerful intelligent assistant that allows you to generate a document authored by the user of the system. The use of large language models opens up wide opportunities for employees in the field of state and municipal administration to automate the process of creating thematic texts, text reports, qualification papers, reviews and analytical notes. It also allows users to see possible new meanings, previously unnoticed associations, and even generate new ideas in the field of management in the process of analyzing the texts received during the abstract. The authors have shown that in order to improve the quality of intellectual abstracting, it is necessary to carry out the iterative use of different methods of teaching (tuning) LLM. At the same time, the initial selection of texts for training, which is made by the user based on his/her own knowledge of the subject area, is important.

Keywords

1. Bakhtizin A.R. (2023) The Challenges of Forecasting under Current Conditions. Ekonomicheskoye vozrozhdeniye Rossii. No. 2(76) P. 53–62. DOI: 10.37930/1990-9780-2023-2(76)-53-62

2. Belyakova A.Yu., Belyakov Yu.D. (2020) Overview of Text Summarization Methods. Inzhenernyy vestnik Dona. No. 10(70). P. 142–159.

3. Bragin A.V., Bakhtizin A.R., Makarov V.L. (2023) Large Fourth-Generation Language Models as a New Tool. Iskusstvennyye obshchestva. Vol. 18. No. 1. DOI: 10.18254/S207751800025046-9

4. Dolgacheva E.L., Kosyuk E.Yu., Popova D.L., Rusakov A.M. (2021) Sovremennyye metody i algoritmy summarizatsii tekstov v zadachakh informatsionnoy bezopasnosti [Modern methods and algorithms of text summarization in information security problems]. Materialy III Mezhdunarodnoy nauchno-prakticheskoy konferentsii “Problemy obespecheniya bezopasnosti (Bezopasnost’-2021)”. V 2-kh tomakh. Ufa: Ufimskiy gosudarstvennyy aviatsionnyy tekhnicheskiy universitet. Vol. 1. P. 287–293

5. Jacobs G., Hoste V. (2020) Extracting Fine-Grained Economic Events from Business News. Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation. Barcelona: online. P. 235–245.

6. Kananykina P.G., Khoroshevsky V.F. (2008) Intellektual’noye referirovaniye: ontologicheskiy podkhod i ego realizatsiya v resheniyakh ONTOS [Intellectual abstracting: An ontological approach and its implementation in ONTOS solutions]. XI natsional’naya konferentsiya po iskusstvennomu intellektu s mezhdunarodnym uchastiyem KII-2008. Moscow: Fizmat-lit. Vol. 2. URL: https://www.raai.org/pages/UGFnZVR5cGU6MTAwNQ==

7. Khurana A., Subramonyam H., Chilana P.K. (2024) Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking? IUI’24: Proceedings of the 29th International Conference on Intelligent User Interfaces. New York: Association for Computing Machinery. P. 288–303. DOI: 10.1145/3640543.3645200

8. Krasochkin S.G. (2023) How ChatGPT Differs from Current Neural Networks. Evraziyskiy Soyuz Uchenykh. Seriya: tekhnicheskiye i fiziko-matematicheskiye nauki. No. 4(107), P. 30–35.

9. Petrunin Yu.Yu. (2023) Development of the Concept of Social Artificial Intelligence. Vestnik Moskovskogo universiteta. Vupusk 21. Upravlenie (gosudarstvo i obchestvo). No. 1. P. 93–112.

10. Reynolds L., McDonell K. (2021) Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm. CHI EA’21: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. New York: Association for Computing Machinery. DOI: 10.1145/3411763.3451760

11. Shao Zh., Gong Y., Shen Y., Huang M., Duan N., Chen W. (2023) Synthetic Prompting: Generating Chain-of- Thought Demonstrations for Large Language Models. Proceedings of the 40th International Conference on Machine Learning. Honolulu, Hawaii: JMLR.org. P. 30706–30775.