{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:16:25Z","timestamp":1757625385654,"version":"3.44.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032025500"},{"type":"electronic","value":"9783032025517"}],"license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-02551-7_10","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:27:45Z","timestamp":1755754065000},"page":"102-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scale-Free Characteristics of\u00a0Multilingual Legal Texts and\u00a0the\u00a0Limitations of\u00a0LLMs"],"prefix":"10.1007","author":[{"given":"Haoyang","family":"Chen","sequence":"first","affiliation":[]},{"given":"Kumiko","family":"Tanaka-Ishii","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"10_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer (2020)"},{"key":"10_CR2","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(null), 993\u20131022 (2003)"},{"issue":"19","key":"10_CR3","doi-asserted-by":"publisher","first-page":"4195","DOI":"10.1016\/j.physa.2010.05.057","volume":"389","author":"MJ Bommarito II","year":"2010","unstructured":"Bommarito, M.J., II., Katz, D.M.: A mathematical approach to the study of the united states code. XXPhys. A 389(19), 4195\u20134200 (2010)","journal-title":"XXPhys. A"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Butler, U.: Open Australian legal corpus (2024). https:\/\/doi.org\/10.57967\/hf\/2784","DOI":"10.57967\/hf\/2784"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Chalkidis, I., Fergadiotis, M., Androutsopoulos, I.: MultiEURLEX - a multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6974\u20136996. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.559","DOI":"10.18653\/v1\/2021.emnlp-main.559"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., Androutsopoulos, I.: LEGAL-BERT: the muppets straight out of law school. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 2898\u20132904. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.261","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Chalkidis, I., Fergadiotis, M., Tsarapatsanis, D., Aletras, N., Androutsopoulos, I., Malakasiotis, P.: Paragraph-level rationale extraction through regularization: a case study on European court of human rights cases. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 226\u2013241. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.22","DOI":"10.18653\/v1\/2021.naacl-main.22"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Chalkidis, I., et al.: LexGLUE: a benchmark dataset for legal language understanding in English. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4310\u20134330. Association for Computational Linguistics, Dublin, Ireland (May 2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.297","DOI":"10.18653\/v1\/2022.acl-long.297"},{"key":"10_CR9","unstructured":"Cover, T.M., Thomas, J.A.: Elements of information theory (1991)"},{"key":"10_CR10","unstructured":"De\u00a0Mulder, R., Van\u00a0Noortwijk, K., Combrink-Kuiters, L.: Jurimetrics please"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Deroy, A., Ghosh, K., Ghosh, S.: Applicability of large language models and generative models for legal case judgement summarization. Artif. Intell. Law (2024). https:\/\/doi.org\/10.1007\/s10506-024-09411-z","DOI":"10.1007\/s10506-024-09411-z"},{"key":"10_CR12","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2021.671882","volume":"9","author":"R Friedrich","year":"2021","unstructured":"Friedrich, R.: Complexity and entropy in legal language. Front. Phys. 9, 671882 (2021). https:\/\/doi.org\/10.3389\/fphy.2021.671882","journal-title":"Front. Phys."},{"issue":"1","key":"10_CR13","doi-asserted-by":"publisher","first-page":"126","DOI":"10.3390\/e22010126","volume":"22","author":"M Gerlach","year":"2020","unstructured":"Gerlach, M., Font-Clos, F.: A standardized project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics. Entropy 22(1), 126 (2020)","journal-title":"Entropy"},{"key":"10_CR14","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. CoRR abs\/2001.08361 (2020)"},{"key":"10_CR15","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s10506-014-9160-8","volume":"22","author":"DM Katz","year":"2014","unstructured":"Katz, D.M., Bommarito, M.J.: Measuring the complexity of the law: the united states code. Artif. Intell. Law 22, 337\u2013374 (2014)","journal-title":"Artif. Intell. Law"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Kobayashi, T., Tanaka-Ishii, K.: Taylor\u2018s law for human linguistic sequences. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1138\u20131148. Association for Computational Linguistics, Melbourne, Australia (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1105","DOI":"10.18653\/v1\/P18-1105"},{"key":"10_CR17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.2307\/1190721","volume":"28","author":"L Loevinger","year":"1963","unstructured":"Loevinger, L.: Jurimetrics: the methodology of legal inquiry. Law Contemp. Probl. 28, 5\u201335 (1963)","journal-title":"Law Contemp. Probl."},{"key":"10_CR18","unstructured":"Manning, C., Schutze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Niklaus, J., Matoshi, V., St\u00fcrmer, M., Chalkidis, I., Ho, D.E.: Multilegalpile: a 689gb multilingual legal corpus (2023)","DOI":"10.18653\/v1\/2024.acl-long.805"},{"key":"10_CR20","unstructured":"OpenAI, Achiam, J., et\u00a0al.: Gpt-4 technical report (2023)"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982\u20133992. Association for Computational Linguistics, Hong Kong, China (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"10_CR22","unstructured":"School, H.L.: Caselaw access project (2024)"},{"issue":"1","key":"10_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebastiani","year":"2002","unstructured":"Sebastiani, F.: Machine learning in automated text categorization. ACM Comput. Surv. 34(1), 1\u201347 (2002). https:\/\/doi.org\/10.1145\/505282.505283","journal-title":"ACM Comput. Surv."},{"issue":"3","key":"10_CR24","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948)","journal-title":"Bell Syst. Tech. J."},{"issue":"3","key":"10_CR25","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1162\/coli_a_00355","volume":"45","author":"S Takahashi","year":"2019","unstructured":"Takahashi, S., Tanaka-Ishii, K.: Evaluating computational language models with scaling properties of natural language. Comput. Linguist. 45(3), 481\u2013513 (2019)","journal-title":"Comput. Linguist."},{"issue":"10","key":"10_CR26","doi-asserted-by":"publisher","first-page":"364","DOI":"10.3390\/e18100364","volume":"18","author":"R Takahira","year":"2016","unstructured":"Takahira, R., Tanaka-Ishii, K., Debowski, L.: Entropy rate estimates for natural language\u2013a new extrapolation of compressed large-scale corpora. Entropy 18(10), 364 (2016). https:\/\/doi.org\/10.3390\/e18100364","journal-title":"Entropy"},{"key":"10_CR27","unstructured":"Takahira, R., Tanaka-Ishii, K., Debowski, \u0141.: Upper bound of entropy rate revisited \u2014a new extrapolation of compressed large-scale corpora\u2014. In: Brunato, D., Dell\u2019Orletta, F., Venturi, G., Fran\u00e7ois, T., Blache, P. (eds.) Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC), pp. 213\u2013221. The COLING 2016 Organizing Committee, Osaka, Japan (2016)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Tanaka-Ishii, K., Kobayashi, T.: Taylor\u2019s law for linguistic sequences and random walk models. J. Phys. Commun. 2(11), 115024 (2018). 089401","DOI":"10.1088\/2399-6528\/aaefb2"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Tanaka-Ishii, K.: Statistical universals of language: Between mathematical chance and human choice (2021)","DOI":"10.1007\/978-3-030-59377-3"},{"issue":"3","key":"10_CR30","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1162\/COLI_a_00228","volume":"41","author":"K Tanaka-Ishii","year":"2015","unstructured":"Tanaka-Ishii, K., Aihara, S.: Computational constancy measures of texts - Yule\u2019s K and R\u00e9nyi\u2019s entropy. Assoc. Comput. Linguist. 41(3), 481\u2013502 (2015)","journal-title":"Assoc. Comput. Linguist."},{"issue":"4766","key":"10_CR31","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1038\/189732a0","volume":"189","author":"LR Taylor","year":"1961","unstructured":"Taylor, L.R.: Aggregation, variance and the mean. Nature 189(4766), 732\u2013735 (1961)","journal-title":"Nature"},{"key":"10_CR32","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023)"},{"key":"10_CR33","unstructured":"Tuggener, D., von D\u00e4niken, P., Peetz, T., Cieliebak, M.: LEDGAR: a large-scale multi-label corpus for text classification of legal provisions in contracts. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1235\u20131241. European Language Resources Association, Marseille, France (2020)"},{"key":"10_CR34","unstructured":"Vladimir\u00a0Vorobev, M.K.: Chatgpt paraphrases dataset (2023)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, Z., Wang, Q., Wei, K., Zhang, K., Shi, J.: Large language models for automated q &a involving legal documents: a survey on algorithms, frameworks and applications. Int. J. Web Inf. Syst. (2023)","DOI":"10.1108\/IJWIS-12-2023-0256"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02551-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:04:33Z","timestamp":1757441073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02551-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025500","9783032025517"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02551-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"22 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Erlangen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}