<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Computational nanotechnology</journal-id><journal-title-group><journal-title xml:lang="en">Computational nanotechnology</journal-title><trans-title-group xml:lang="ru"><trans-title>Computational nanotechnology</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2313-223X</issn><issn publication-format="electronic">2587-9693</issn><publisher><publisher-name xml:lang="en">YUR-VAK</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">350202</article-id><article-id pub-id-type="doi">10.33693/2313-223X-2025-12-3-209-220</article-id><article-id pub-id-type="edn">CBJQVM</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>LARGE LANGUAGE MODELS IN LEGAL PRACTICE</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>БОЛЬШИЕ ЯЗЫКОВЫЕ МОДЕЛИ В ЮРИДИЧЕСКОЙ ПРАКТИКЕ</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Evolution of the capabilities of large language models in the legal field: Meta-analysis of four experimental studies</article-title><trans-title-group xml:lang="ru"><trans-title>Эволюция возможностей больших языковых моделей в юридической сфере: метаанализ четырех экспериментальных исследований</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4789-0736</contrib-id><contrib-id contrib-id-type="spin">1371-0337</contrib-id><name-alternatives><name xml:lang="en"><surname>Dushkin</surname><given-names>Roman V.</given-names></name><name xml:lang="ru"><surname>Душкин</surname><given-names>Роман Викторович</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>senior lecturer, Department 22 “Cybernetics”</p></bio><bio xml:lang="ru"><p>старший преподаватель, кафедра 22 «Кибернетика»</p></bio><email>drv@aia.expert</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6485-8135</contrib-id><contrib-id contrib-id-type="spin">9587-1028</contrib-id><name-alternatives><name xml:lang="en"><surname>Podoprigora</surname><given-names>Vladimir N.</given-names></name><name xml:lang="ru"><surname>Подопригора</surname><given-names>Владимир Николаевич</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Cand. Sci. (Econ.), head of the laboratory</p></bio><bio xml:lang="ru"><p>кандидат экономических наук, руководитель лаборатории</p></bio><email>Podoprigora.VN@rea.ru</email><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Kuzmin</surname><given-names>Alexey A.</given-names></name><name xml:lang="ru"><surname>Кузьмин</surname><given-names>Алексей Алексеевич</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>general director</p></bio><bio xml:lang="ru"><p>генеральный директор</p></bio><email>a.kuzmin@edisai.tech</email><xref ref-type="aff" rid="aff3"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Dushkin</surname><given-names>Kirill R.</given-names></name><name xml:lang="ru"><surname>Душкин</surname><given-names>Кирилл Романович</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>analyst</p></bio><bio xml:lang="ru"><p>аналитик</p></bio><email>dkr@aia.expert</email><xref ref-type="aff" rid="aff4"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">National Research Nuclear University “MEPhI”</institution></aff><aff><institution xml:lang="ru">Национальный исследовательский ядерный университет «МИФИ»</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">Plekhanov Russian University of Economics</institution></aff><aff><institution xml:lang="ru">Российский экономический университет имени Г.В. Плеханова</institution></aff></aff-alternatives><aff-alternatives id="aff3"><aff><institution xml:lang="en">Ecosystem Digital Solutions LLC</institution></aff><aff><institution xml:lang="ru">ООО «Экосистемные цифровые решения»</institution></aff></aff-alternatives><aff-alternatives id="aff4"><aff><institution xml:lang="en">A-Ya expert LLC</institution></aff><aff><institution xml:lang="ru">ООО «А-Я эксперт»</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-11-02" publication-format="electronic"><day>02</day><month>11</month><year>2025</year></pub-date><volume>12</volume><issue>3</issue><fpage>209</fpage><lpage>220</lpage><history><date date-type="received" iso-8601-date="2025-11-07"><day>07</day><month>11</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Yur-VAK</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Юр-ВАК</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Yur-VAK</copyright-holder><copyright-holder xml:lang="ru">Юр-ВАК</copyright-holder><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://www.urvak.ru/contacts/</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.rcsi.science/2313-223X/article/view/350202">https://journals.rcsi.science/2313-223X/article/view/350202</self-uri><abstract xml:lang="en"><p>This paper presents a meta-analysis of four experimental studies from the Norm! project, aimed at systematically studying the effectiveness of large language models in the legal field. The study includes a comparative analysis of junior and senior models, optimization of system prompts, and testing of multi-agent architectures on tasks in Russian family and civil law. A key discovery was the identification of a nonlinear relationship between architectural complexity and the quality of results: the transition from simple to complex systems provides a slight increase in quality (15–40%) with an exponential increase in resource costs (by a factor of 10–15). The flagship models GPT-4.1 and Gemini 2.5 Pro demonstrate superior quality (9.04 and 8.52 points), but junior LLMs with efficiency coefficients up to 130.3 remain cost-effective. A universal problem area for all architectures is tasks requiring an integrative analysis of multiple legal norms. The results form scientifically sound recommendations for various implementation scenarios: from mass consulting services to specialized legal applications, defining the prospects for the development of hybrid architectures in legal practice.</p></abstract><trans-abstract xml:lang="ru"><p>Представлен метаанализ четырех экспериментальных исследований проекта «Норм!», направленный на систематическое изучение эффективности больших языковых моделей в юридической сфере. Исследование охватывает сравнительный анализ младших и старших моделей, оптимизацию системных промптов и тестирование многоагентных архитектур на задачах по российскому семейному и гражданскому праву. Ключевым открытием стало выявление нелинейной зависимости между архитектурной сложностью и качеством результатов: переход от простых к сложным системам обеспечивает незначительный прирост качества (15–40%) при экспоненциальном росте ресурсных затрат (в 10–15 раз). Флагманские модели GPT-4.1 и Gemini 2.5 Pro демонстрируют превосходство по качеству (9,04 и 8,52 балла), однако экономически оптимальными остаются младшие БЯМ с коэффициентами эффективности до 130.3. Универсальной проблемной зоной для всех архитектур являются задачи, требующие интегративного анализа множественных правовых норм. Результаты формируют научно обоснованные рекомендации для различных сценариев внедрения: от массовых консультационных сервисов до специализированных юридических применений, определяя перспективы развития гибридных архитектур в правовой практике.</p></trans-abstract><kwd-group xml:lang="en"><kwd>large language models</kwd><kwd>legal artificial intelligence</kwd><kwd>meta-analysis</kwd><kwd>multi-agent systems</kwd><kwd>system prompts</kwd><kwd>cost-effectiveness</kwd><kwd>legal consulting</kwd><kwd>RAG systems</kwd><kwd>family law</kwd><kwd>artificial intelligence system architecture</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>большие языковые модели</kwd><kwd>юридический искусственный интеллект</kwd><kwd>метаанализ</kwd><kwd>многоагентные системы</kwd><kwd>системные промпты</kwd><kwd>экономическая эффективность</kwd><kwd>правовое консультирование</kwd><kwd>RAG-системы</kwd><kwd>семейное право</kwd><kwd>архитектура систем искусственного интеллекта</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><citation-alternatives><mixed-citation xml:lang="en">Dushkin R.V. Artificial Intelligence. Moscow: DMK-Press, 2019. 280 p. ISBN: 978-5-97060-787-9.</mixed-citation><mixed-citation xml:lang="ru">Душкин Р.В. Искусственный интеллект. М.: ДМК-Пресс, 2019. 280 с. ISBN: 978-5-97060-787-9.</mixed-citation></citation-alternatives></ref><ref id="B2"><label>2.</label><citation-alternatives><mixed-citation xml:lang="en">Lai J., Gan W., Wu J. et al. Large language models in law: A survey. AI Open. 2024. URL: https://www.sciencedirect.com/science/article/pii/S2666651024000172 (data of accesses: 13.10.2023).</mixed-citation><mixed-citation xml:lang="ru">Lai J., Gan W., Wu J. et al. Large language models in law: A survey // AI Open. 2024. URL: https://www.sciencedirect.com/science/article/pii/S2666651024000172 (data of accesses: 13.10.2023).</mixed-citation></citation-alternatives></ref><ref id="B3"><label>3.</label><citation-alternatives><mixed-citation xml:lang="en">Ma S., Chen C., Chu Q. et al. Leveraging large language models for relevance judgments in legal case retrieval. arXiv preprint arXiv:2403.18405. 2024. URL: https://arxiv.org/abs/2403.18405 (data of accesses: 13.10.2023).</mixed-citation><mixed-citation xml:lang="ru">Ma S., Chen C., Chu Q. et al. Leveraging large language models for relevance judgments in legal case retrieval // arXiv preprint arXiv:2403.18405. 2024. URL: https://arxiv.org/abs/2403.18405 (data of accesses: 13.10.2023).</mixed-citation></citation-alternatives></ref><ref id="B4"><label>4.</label><citation-alternatives><mixed-citation xml:lang="en">Paul V. Automation in legal: The increasing role of AI. Medium. 2024. URL: https://medium.com/@vincentpaulai/automation-in-legal-the-increasing-role-of-ai-70724ef0b225 (data of accesses: 13.10.2023).</mixed-citation><mixed-citation xml:lang="ru">Paul V. Automation in legal: The increasing role of AI // Medium. 2024. URL: https://medium.com/@vincentpaulai/automation-in-legal-the-increasing-role-of-ai-70724ef0b225 (data of accesses: 13.10.2023).</mixed-citation></citation-alternatives></ref><ref id="B5"><label>5.</label><citation-alternatives><mixed-citation xml:lang="en">Magesh V., Surani F., Dahl M. et al. Hallucination-free? Assessing the reliability of leading AI legal research tools. arXiv preprint arXiv:2405.20362. 2024. URL: https://arxiv.org/abs/2405.20362 (data of accesses: 13.10.2023).</mixed-citation><mixed-citation xml:lang="ru">Magesh V., Surani F., Dahl M. et al. Hallucination-free? Assessing the reliability of leading AI legal research tools // arXiv preprint arXiv:2405.20362. 2024. URL: https://arxiv.org/abs/2405.20362 (data of accesses: 13.10.2023).</mixed-citation></citation-alternatives></ref><ref id="B6"><label>6.</label><citation-alternatives><mixed-citation xml:lang="en">The future of artificial intelligence in the legal industry: Opportunities, challenges, and ethical considerations. Legal Stuff. URL: https://medium.com/@legal.stuff.notion/the-future-of-artificial-intelligence-in-the-legal-industry-opportunities-challenges-and-ethical-61c3198b425a (data of accesses: 13.10.2023).</mixed-citation><mixed-citation xml:lang="ru">The future of artificial intelligence in the legal industry: Opportunities, challenges, and ethical considerations // Legal Stuff. URL: https://medium.com/@legal.stuff.notion/the-future-of-artificial-intelligence-in-the-legal-industry-opportunities-challenges-and-ethical-61c3198b425a (data of accesses: 13.10.2023).</mixed-citation></citation-alternatives></ref><ref id="B7"><label>7.</label><citation-alternatives><mixed-citation xml:lang="en">Korneenkov A.A., Yanov Yu.K., Ryazantsev S.V. et al. Meta-analysis of clinical studies in otorhinolaryngology. Bulletin of Otorhinolaryngology. 2020. Vol. 85. No. 2. Pp. 26–30. (In Rus.). DOI: 10.17116/otorino20208502126.</mixed-citation><mixed-citation xml:lang="ru">Корнеенков А.А., Янов Ю.К., Рязанцев С.В. и др. Метаанализ клинических исследований в оториноларингологии // Вестник оториноларингологии. 2020. Т. 85. № 2. С. 26–30. DOI: 10.17116/otorino20208502126.</mixed-citation></citation-alternatives></ref><ref id="B8"><label>8.</label><citation-alternatives><mixed-citation xml:lang="en">Dushkin R.V. Overview of approaches and methods of artificial intelligence. Radio Electronic Technologies. 2018. No. 3. Pp. 85–89. (In Rus.)</mixed-citation><mixed-citation xml:lang="ru">Душкин Р.В. Обзор подходов и методов искусственного интеллекта // Радиоэлектронные технологии. 2018. № 3. С. 85–89.</mixed-citation></citation-alternatives></ref><ref id="B9"><label>9.</label><citation-alternatives><mixed-citation xml:lang="en">Rumyantsev P.O., Saenko U.V., Rumyantseva U.V. Statistical methods of analysis in clinical practice. Part 1. Univariate statistical analysis. Problems of Endocrinology. 2009. Vol. 55. No. 5. Pp. 48–55. (In Rus.). DOI: 10.14341/probl200955548-55.</mixed-citation><mixed-citation xml:lang="ru">Румянцев П.О., Саенко У.В., Румянцева У.В. Статистические методы анализа в клинической практике. Ч. 1. Одномерный статистический анализ // Проблемы эндокринологии. 2009. Т. 55. № 5. С. 48–55. DOI: 10.14341/probl200955548-55.</mixed-citation></citation-alternatives></ref><ref id="B10"><label>10.</label><citation-alternatives><mixed-citation xml:lang="en">Dushkin R.V. Why hybrid AI systems hold the future. Economic Strategies. 2018. No. 6 (156). Pp. 84–93. (In Rus.)</mixed-citation><mixed-citation xml:lang="ru">Душкин Р.В. Почему за гибридными ИИ-системами будущее // Экономические стратегии. 2018. № 6 (156). С. 84–93.</mixed-citation></citation-alternatives></ref></ref-list></back></article>
