Methods and Techniques for Semi-Automatic Structuring and Evaluation of the Text of a Scientific Article: Review and Prospects for the Development of Information System
DOI:
https://doi.org/10.17072/1993-0550-2026-1-131-143Keywords:
structuring and evaluation of the text, , natural language processing, NLP, large language models, LLM, academic writing, artificial intelligenceAbstract
The article describes the problem of obtaining timely and high-quality feedback on scientific articles from peer-reviewers and considers the feasibility of using AI to solve it. A systematic description of existing commercial and research solutions for structuring and text quality evaluation (Writefull, Grammarly, Quillbot, ChatGPT, etc.) is provided, their advantages and disadvantages are analyzed. Various approaches and architectures are studied, and their effectiveness in structuring and evaluating scientific texts is compared. IMRAD was chosen as the target structure for scientific articles due to its versatility, flexibility, and applicability in various fields. Based on the analysis, requirements for a system for structuring and evaluation of the scientific article text were formulated. A modular section-based architecture of an information system integrated into a text editor is proposed. The system includes four modules: "Sentence Templates", "Text Structure Evaluation", "Text Style Evaluation", and "Text Clarity and Logic Evaluation". A distinctive feature of the proposed architecture is the use of AI agents (instances of a large language model) to analyze individual aspects of the text while taking into an account the context between sections of the IMRAD structure (introduction, methods, results, discussion). Technical and methodological limitations of implementing such systems are discussed. The presented study can serve as a basis for the development of an information system.References
Reflections on the 2025 Review Process from the Program Committee Chairs [Электронный ресурс]. URL: https://blog.neurips.cc/2025/09/30/reflections-on-the-2025-review-process-from-the-program-committee-chairs/#:~:text=Like%20most%20AI%20conferences%2C%20NeurIPS,not%20only%20is%20a%20challenge (дата обращения: 19.01.2026).
Gottweis J. и др. Towards an AI co-scientist [Электронный ресурс]. URL: https://arxiv.org/pdf/2502.18864 (дата обращения: 19.01.2026).
Liang W. и др. Can Large Language Models Provide Useful Feedback on Research Papers? A Large-Scale Empirical Analysis // NEJM AI. 2024. V. 1, No 8.
Телицына А. Ю. Оптимизация научной деятельности через интеграцию ИИ: нейронные сети как инструмент в работе с академической литературой // Мониторинг общественного мнения: экономические и социальные перемены. 2024. № 5.
Cheng A., Calhoun A., Reedy G. Artificial intelligence-assisted academic writing: recommendations for ethical use // Advances in Simulation. 2025. V. 10, No 1. P. 22.
Sollaci L. B., Pereira M. G. The introduction, methods, results, and discussion (IMRAD) structure: a fifty-year survey. // J. Med. Libr. Assoc. 2004. V. 92, No 3. P. 364–367.
Moskovitz C., Harmon B., Saha S. The Structure of Scientific Writing: An Empirical Analysis of Recent Research Articles in STEM // Journal of Technical Writing and Communication. 2024. V. 54, No 3. P. 265–281.
Tokdemir Demirel E. The Use and Perceptions Towards AI Tools For Academic Writing Among University Students // Innovations in Language Teaching Journal. 2024. V. 1, No 1. P. 1–20.
Khalifa M., Albadawy M. Using artificial intelligence in academic writing and research: An essential productivity tool // Computer Methods and Programs in Biomedicine Update. 2024. V. 5. P. 100145(11).
Granjeiro J. M. и др. The Future of Scientific Writing: AI Tools, Benefits, and Ethical Implications // Braz. Dent. J. 2025. V. 36. DOI: 10.1590/0103-644020256471.
Pividori M., Greene C. S. A publishing infrastructure for AI-assisted academic authoring // Journal of the American Medical Informatics Association (JAMIA). 2023. V. 31, No 9. P. 2103–2113.
Arcy M. D. и др. MARG: Multi-Agent Review Generation for Scientific Papers [Электронный ресурс]. URL: https://arxiv.org/pdf/2401.04259 (дата обращения: 19.01.2026).
Jin Y. и др. AgentReview: Exploring Peer Review Dynamics with LLM Agents [Электронный ресурс]. URL: https://arxiv.org/abs/2406.12708 (дата обращения: 19.01.2026).
Schmidgall S. и др. Agent Laboratory: Using LLM Agents as Research Assistants. Association for Computational Linguistics (ACL), 2025. P. 5977–6043.
Chen N. и др. XtraGPT: Context-Aware and Controllable Academic Paper Revision. 2025 [Электронный ресурс]. URL: https://arxiv.org/pdf/2505.11336 (дата обращения: 19.01.2026).
Du W. и др. Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision // Proceedings of the First Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2022). Stroudsburg, PA, USA: Association for Computational Linguistics, 2022. P. 96–108.
Nguyen A. и др. Human-AI collaboration patterns in AI-assisted academic writing // Studies in Higher Education. 2024. V. 49, No 5. P. 847–864.
Deep P. Das, Chen Y. The Role of AI in Academic Writing: Impacts on Writing Skills, Critical Thinking, and Integrity in Higher Education // Societies. 2025. V. 15, No 9. P. 247.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Александр Александрович Толстенко, Екатерина Владимировна Исаева
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are published under license Creative Commons Attribution 4.0 International (CC BY 4.0).
