<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" 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" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2026-26-4-860-867</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-654</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Метод построения RAG для анализа гетерогенных графо-иерархических текстовых корпусов</article-title><trans-title-group xml:lang="en"><trans-title>RAG construction method for heterogeneous graph-hierarchical text corpus analysis</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0001-2374-8025</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Улизько</surname><given-names>М. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Ulizko</surname><given-names>M. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Улизько Максим Валерьевич — преподаватель</p><p>sc 60149361200</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Maxim V. Ulizko — Lecturer</p><p>sc 60149361200</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">ulizko@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-4646-6856</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Береснев</surname><given-names>А. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Beresnev</surname><given-names>A. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Береснев Артем Дмитриевич — кандидат технических наук, доцент</p><p>sc 57202210221</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Artem D. Beresnev — PhD, Associate Professor</p><p>sc 57202210221</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">artem.beresnev@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-2082-7433</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Жуков</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Zhukov</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Жуков Вадим Витальевич — аспирант</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Vadim V. Zhukov — PhD Student</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">pdf.markov@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-4176-7931</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Марков</surname><given-names>П. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Markov</surname><given-names>P. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Марков Петр Денисович — главный разработчик</p><p>Москва, 119048</p></bio><bio xml:lang="en"><p>Petr D. Markov — Leading Developer</p><p>Saint Petersburg</p></bio><email xlink:type="simple">natfed@list.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1361-6037</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусарова</surname><given-names>Н. Ф.</given-names></name><name name-style="western" xml:lang="en"><surname>Gusarova</surname><given-names>N. F.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гусарова Наталия Федоровна — кандидат технических наук, старший научный сотрудник, доцент</p><p>sc 57162764200</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Natalia F. Gusarova — PhD, Senior Researcher, Associate Professor</p><p>sc 57162764200</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">natfed@list.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ПАО «БАНК УРАЛСИБ»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>PJSC “Bank Uralsib”</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>27</day><month>08</month><year>2026</year></pub-date><volume>26</volume><issue>4</issue><fpage>860</fpage><lpage>867</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Улизько М.В., Береснев А.Д., Жуков В.В., Марков П.Д., Гусарова Н.Ф., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Улизько М.В., Береснев А.Д., Жуков В.В., Марков П.Д., Гусарова Н.Ф.</copyright-holder><copyright-holder xml:lang="en">Ulizko M.V., Beresnev A.D., Zhukov V.V., Markov P.D., Gusarova N.F.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/654">https://ntv.elpub.ru/jour/article/view/654</self-uri><abstract><p>Введение. Анализ корпусов документов со сложными внутренними и междокументными связями требует не только поиска релевантных текстов, но и построения минимального, проверяемого и трассируемого набора фрагментов, достаточного для последующего вывода и цитирования. В работе предложен метод извлечения фрагментов для корпусов документов, в котором смысл фрагмента определяется его локальным содержанием, положением в структуре документа и системой ссылок на другие фрагменты. Метод. Разработанный метод основан на совместном представлении корпуса как дерева структурных единиц и ориентированного графа ссылок, а также на гибридном ранжировании, сочетающем лексический поиск, векторное сходство и ссылочный сигнал. Доказана монотонность и субмодулярность целевой функции, что позволяет применять жадные алгоритмы с известной аппроксимационной гарантией и выполнять бюджетированный отбор контекста для системы генерации с дополненным поиском (Retrieval-Augmented Generation, RAG). Дополнительновводится протокол оценки, разделяющий качество извлечения на уровне документов, фрагментов и цитат. Основные результаты. Представленный метод формально валидирован на тестах устойчивости к лексическому несовпадению и эффективности бюджетного отбора по сравнению с простыми стратегиями. Для содержательной иллюстрации эффективности метода использованы примеры из юридического домена. Обсуждение. Метод может использоваться как слой извлечения для RAG-систем в задачах построения вопросно-ответных систем, поиска доказательств, нормативного комплаенса и анализа больших структурно связанных корпусов.</p></abstract><trans-abstract xml:lang="en"><p> Analysis of document corpora with complex internal and inter-document links requires not only retrieval of relevant texts but also construction of a compact, verifiable and traceable set of fragments sufficient for downstream reasoning and citation. The purpose of this work is to propose a fragment retrieval method for document corpora in which the meaning of a fragment is determined by its local content, position in the document hierarchy and links to other fragments. The method is based on a joint representation of the corpus as a tree of structural units and a directed link graph as well as on hybrid ranking that combines lexical search, vector similarity, and a link signal. The monotonicity and submodularity of the objective function are shown, which makes it possible to use greedy algorithms with a known approximation guarantee and to perform budgeted context selection for a Retrieval-Augmented Generation (RAG) system. In addition, an evaluation protocol is introduced that separates retrieval quality at the document, fragment, and citation levels. The method is formally validated on tests of lexical mismatch robustness and budgeted selection efficiency compared with simple strategies. Examples from the legal domain are used to illustrate the method. The method can be used as a retrieval layer for RAG systems in question answering, evidence retrieval, regulatory compliance, and analysis of large structurally connected corpora.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>интеллектуальный анализ документов</kwd><kwd>граф ссылок</kwd><kwd>графо-иерархическая структура корпуса</kwd><kwd>RAG-система</kwd><kwd>бюджетированный отбор контекста</kwd><kwd>извлечение информации</kwd><kwd>поиск доказательств</kwd><kwd>субмодулярная оптимизация</kwd><kwd>юридические документы</kwd></kwd-group><kwd-group xml:lang="en"><kwd>intelligent document analysis</kwd><kwd>link graph</kwd><kwd>graph-hierarchical corpus structure</kwd><kwd>RAG system</kwd><kwd>budgeted context selection</kwd><kwd>information extraction</kwd><kwd>evidence retrieval</kwd><kwd>submodular optimization</kwd><kwd>legal documents</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Работа частично поддержана Министерством науки и высшего образования Российской Федерации, госзадание FSER-2025-0013.</funding-statement><funding-statement xml:lang="en">This work was partly supported by the Ministry of Science and Higher Education of the Russian Federation, State Assignment FSER-2025-0013.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Gao Y., Xiong Y., Gao X., Jia K., Pan J., Bi Y., et al. Retrievalaugmented generation for Large Language Models: a survey // arXiv. 2024. arXiv:2312.10997. doi: 10.48550/arXiv.2312.10997</mixed-citation><mixed-citation xml:lang="en">Gao Y., Xiong Y., Gao X., Jia K., Pan J., Bi Y., et al. Retrievalaugmented generation for Large Language Models: a survey. arXiv, 2024. arXiv:2312.10997. doi: 10.48550/arXiv.2312.10997</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Barnett S., Kurniawan S., Thudumu S., Brannelly Z., Abdelrazek M. Seven failure points when engineering a retrieval augmented generation system // Proc. of the IEEE/ACM 3rd International Conference on AI Engineering — Software Engineering for AI. 2024. P. 194–199. doi: 10.1145/3644815.3644945</mixed-citation><mixed-citation xml:lang="en">Barnett S., Kurniawan S., Thudumu S., Brannelly Z., Abdelrazek M. Seven failure points when engineering a retrieval augmented generation system. Proc. of the IEEE/ACM 3rd International Conference on AI Engineering — Software Engineering for AI, 2024, pp. 194–199. doi: 10.1145/3644815.3644945</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Jin B., Yoon J., Han J., Arik S.O. Long-context LLMs meet RAG: overcoming challenges for long inputs in RAG // Proc. of the International Conference on Learning Representations. 2025.</mixed-citation><mixed-citation xml:lang="en">Jin B., Yoon J., Han J., Arik S.O. Long-context LLMs meet RAG: overcoming challenges for long inputs in RAG. Proc. of the International Conference on Learning Representations, 2025.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., et al. Retrieval-augmented generation for knowledge-intensive NLP tasks // Proc. of the 34th International Conference on Neural Information Processing Systems. 2020. P. 9459–9474.</mixed-citation><mixed-citation xml:lang="en">Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Proc. of the 34th International Conference on Neural Information Processing Systems, 2020, pp. 9459–9474.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Pipitone N., Alami G.H. LegalBench-RAG: a benchmark for retrievalaugmented generation in the legal domain // arXiv. 2024. arXiv:2408.10343. doi: 10.48550/arXiv.2408.10343</mixed-citation><mixed-citation xml:lang="en">Pipitone N., Alami G.H. LegalBench-RAG: a benchmark for retrievalaugmented generation in the legal domain. arXiv, 2024. arXiv:2408.10343. doi: 10.48550/arXiv.2408.10343</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Reuter M., Lingenberg T., Liepina R., Lagioia F., Lippi M., Sartor G., et al. Towards reliable retrieval in RAG systems for large legal datasets // Proc. of the Natural Legal Language Processing Workshop. 2025. P. 17–30. doi: 10.18653/v1/2025.nllp-1.3</mixed-citation><mixed-citation xml:lang="en">Reuter M., Lingenberg T., Liepina R., Lagioia F., Lippi M., Sartor G., et al. Towards reliable retrieval in RAG systems for large legal datasets. Proc. of the Natural Legal Language Processing Workshop, 2025, pp. 17–30. doi: 10.18653/v1/2025.nllp-1.3</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Zheng L., Guha N., Arifov J., Zhang S., Skreta M., Manning C.D., et al. A Reasoning-focused legal retrieval benchmark // Proc. of the 2025 Symposium on Computer Science and Law. 2025. P. 169–193. doi: 10.1145/3709025.3712219</mixed-citation><mixed-citation xml:lang="en">Zheng L., Guha N., Arifov J., Zhang S., Skreta M., Manning C.D., et al. A Reasoning-focused legal retrieval benchmark. Proc. of the 2025 Symposium on Computer Science and Law, 2025, pp. 169–193. doi: 10.1145/3709025.3712219</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Latif S., Ameer H., Akram M.H., Fatima M. The chunking paradigm: pecursive semantic for RAG optimization // Proc. of the 8th International Conference on Natural Language and Speech Processing (ICNLSP-2025). 2025. P. 137–145.</mixed-citation><mixed-citation xml:lang="en">Latif S., Ameer H., Akram M.H., Fatima M. The chunking paradigm: pecursive semantic for RAG optimization. Proc. of the 8th International Conference on Natural Language and Speech Processing (ICNLSP-2025), 2025, pp. 137–145.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Gunther M., Mohr I., Williams D.J., Wang B., Xiao H. Late chunking: contextual chunk embeddings using long-context embedding models // arXiv. 2024. arXiv:2409.04701. doi: 10.48550/arXiv.2409.04701</mixed-citation><mixed-citation xml:lang="en">Gunther M., Mohr I., Williams D.J., Wang B., Xiao H. Late chunking: contextual chunk embeddings using long-context embedding models. arXiv, 2024. arXiv:2409.04701. doi: 10.48550/arXiv.2409.04701</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Qu R., Tu R., Bao F.S. Is semantic chunking worth the computational cost? // Findings of the Association for Computational Linguistics: NAACL. 2025. P. 2155–2177. doi: 10.18653/v1/2025.findingsnaacl.114</mixed-citation><mixed-citation xml:lang="en">Qu R., Tu R., Bao F.S. Is semantic chunking worth the computational cost? Findings of the Association for Computational Linguistics: NAACL, 2025, pp. 2155–2177. doi: 10.18653/v1/2025.findingsnaacl.114</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Shin J., Park C., Park J., Seo J., Lim H. MultiDocFusion: hierarchical and multimodal chunking pipeline for enhanced RAG on long industrial documents // Proc. of the Conference on Empirical Methods in Natural Language Processing. 2025. P. 20985–21004. doi: 10.18653/v1/2025.emnlp-main.1062</mixed-citation><mixed-citation xml:lang="en">Shin J., Park C., Park J., Seo J., Lim H. MultiDocFusion: hierarchical and multimodal chunking pipeline for enhanced RAG on long industrial documents. Proc. of the Conference on Empirical Methods in Natural Language Processing, 2025, pp. 20985–21004. doi: 10.18653/v1/2025.emnlp-main.1062</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Sarthi P., Abdullah S., Tuli A., Khanna S., Goldie A., Manning C.D. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval // Proc. of the International Conference on Learning Representations. 2024.</mixed-citation><mixed-citation xml:lang="en">Sarthi P., Abdullah S., Tuli A., Khanna S., Goldie A., Manning C.D. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval. Proc. of the International Conference on Learning Representations, 2024.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Robertson S., Zaragoza H. The Probabilistic relevance framework: BM25 and beyond // Foundations and Trends in Information Retrieval. 2009. V. 3. N 4. P. 333–389. doi: 10.1561/1500000019</mixed-citation><mixed-citation xml:lang="en">Robertson S., Zaragoza H. The Probabilistic relevance framework: BM25 and beyond. Foundations and Trends in Information Retrieval, 2009. vol. 3, no. 4, pp. 333–389. doi: 10.1561/1500000019</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Santhanam K., Khattab O., Saad-Falcon J., Potts C., Zaharia M. ColBERTv2: Effective and efficient retrieval via lightweight late interaction // Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022. P. 3715–3734. doi: 10.18653/v1/2022.naacl-main.272</mixed-citation><mixed-citation xml:lang="en">Santhanam K., Khattab O., Saad-Falcon J., Potts C., Zaharia M. ColBERTv2: Effective and efficient retrieval via lightweight late interaction. Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022, pp. 3715–3734. doi: 10.18653/v1/2022.naacl-main.272</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Khuller S., Moss A., Naor J. The budgeted maximum coverage problem // Information Processing Letters. 1999. V. 70. N 1. P. 39–45. doi: 10.1016/S0020-0190(99)00031-9</mixed-citation><mixed-citation xml:lang="en">Khuller S., Moss A., Naor J. The budgeted maximum coverage problem. Information Processing Letters, 1999, vol. 70, no. 1, pp. 39-45. doi: 10.1016/S0020-0190(99)00031-9</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Lin H., Bilmes J. A class of submodular functions for document summarization // Proc. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. 2011. P. 510–520.</mixed-citation><mixed-citation xml:lang="en">Lin H., Bilmes J. A class of submodular functions for document summarization. Proc. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011, pp. 510–520.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Sviridenko M. A note on maximizing a submodular set function subject to a knapsack constraint // Operations Research Letters. 2004. V. 32. N 1. P. 41–43. doi: 10.1016/S0167-6377(03)00062-2</mixed-citation><mixed-citation xml:lang="en">Sviridenko M. A note on maximizing a submodular set function subject to a knapsack constraint. Operations Research Letters, 2004, vol. 32, no. 1, pp. 41–43. doi: 10.1016/S0167-6377(03)00062-2</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Saveliev D., Kuchakov R. The Russian legislative corpus // arXiv. 2024. arXiv:2406.04855. doi: 10.48550/arXiv.2406.04855</mixed-citation><mixed-citation xml:lang="en">Saveliev D., Kuchakov R. The Russian legislative corpus. arXiv, 2024. arXiv:2406.04855. doi: 10.48550/arXiv.2406.04855</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Koreeda Y., Manning C. ContractNLI: a dataset for document-level natural language inference for contracts // Findings of the Association for Computational Linguistics: EMNLP. 2021. P. 1907–1919. doi: 10.18653/v1/2021.findings-emnlp.164</mixed-citation><mixed-citation xml:lang="en">Koreeda Y., Manning C. ContractNLI: a dataset for document-level natural language inference for contracts. Findings of the Association for Computational Linguistics: EMNLP, 2021, pp. 1907–1919. doi: 10.18653/v1/2021.findings-emnlp.164</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Wang S.H., Scardigli A., Tang L., Chen W., Levkin D., Chen A., et al. MAUD: an expert-annotated legal NLP dataset for merger agreement understanding // Proc. of the Conference on Empirical Methods in Natural Language Processing. 2023. P. 16369–16382. doi: 10.18653/v1/2023.emnlp-main.1019</mixed-citation><mixed-citation xml:lang="en">Wang S.H., Scardigli A., Tang L., Chen W., Levkin D., Chen A., et al. MAUD: an expert-annotated legal NLP dataset for merger agreement understanding. Proc. of the Conference on Empirical Methods in Natural Language Processing, 2023, pp. 16369–16382. doi: 10.18653/v1/2023.emnlp-main.1019</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Hendrycks D., Burns C., Chen A., Ball S. CUAD: an expert-annotated NLP dataset for legal contract review // arXiv. 2021. arXiv:2103.06268. doi: 10.48550/arXiv.2103.06268</mixed-citation><mixed-citation xml:lang="en">Hendrycks D., Burns C., Chen A., Ball S. CUAD: an expert-annotated NLP dataset for legal contract review. arXiv, 2021. arXiv:2103.06268. doi: 10.48550/arXiv.2103.06268</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
