{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:54:10Z","timestamp":1778172850088,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008984","name":"Indian Institute of Technology Kharagpur","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008984","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Law"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The escalating number of pending cases is a growing concern worldwide. Recent advancements in digitization have opened up possibilities for leveraging artificial intelligence (AI) tools in the processing of legal documents. Adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. With the aim of achieving this objective, we put forward a set of diverse attributes for criminal case proceedings. To enhance the effectiveness of automatically extracting these attributes from legal documents within a sequence labeling framework, we propose the utilization of a few-shot learning approach based on Large Language Models (LLMs). Moreover, we demonstrate the efficacy of the extracted attributes in downstream tasks, such as\n                    <jats:italic>legal judgment prediction and legal statute prediction<\/jats:italic>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s10506-024-09425-7","type":"journal-article","created":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T23:24:27Z","timestamp":1731281067000},"page":"245-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A case study for automated attribute extraction from legal documents using large language models"],"prefix":"10.1007","volume":"34","author":[{"given":"Subinay","family":"Adhikary","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3814-5462","authenticated-orcid":false,"given":"Procheta","family":"Sen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dwaipayan","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kripabandhu","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,11]]},"reference":[{"key":"9425_CR1","first-page":"367","volume":"379","author":"S Adhikary","year":"2023","unstructured":"Adhikary S, Roy D, Ganguly D, Kumar Guha S, Ghosh K (2023) Leda: a system for legal data annotation. Front Art Intel Appl 379:367\u2013370","journal-title":"Front Art Intel Appl"},{"issue":"5","key":"9425_CR2","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1016\/j.jksuci.2019.11.015","volume":"34","author":"D Anand","year":"2022","unstructured":"Anand D, Wagh R (2022) Effective deep learning approaches for summarization of legal texts. J King Saud Univ- Computer Inf Sci 34(5):2141\u20132150. https:\/\/doi.org\/10.1016\/j.jksuci.2019.11.015","journal-title":"J King Saud Univ- Computer Inf Sci"},{"issue":"6","key":"9425_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103069","volume":"59","author":"P Bhattacharya","year":"2022","unstructured":"Bhattacharya P, Ghosh K, Pal A, Ghosh S (2022) Legal case document similarity: you need both network and text. Inf Proc Manage 59(6):103069","journal-title":"Inf Proc Manage"},{"key":"9425_CR4","doi-asserted-by":"crossref","unstructured":"Bhattacharya P, Poddar S, Rudra K, Ghosh K, Ghosh S (2021) Incorporating domain knowledge for extractive summarization of legal case documents. Proc. of ICAIL","DOI":"10.1145\/3462757.3466092"},{"key":"9425_CR5","doi-asserted-by":"crossref","unstructured":"Bhattacharya P, Paul S, Ghosh K, Ghosh S, Wyner A (2019) Identification of rhetorical roles of sentences in indian legal judgments. In: Araszkiewicz, M., Rodr\u00edguez-Doncel, V. (eds) Legal Knowledge and Information Systems - JURIX 2019: The Thirty-second Annual Conference","DOI":"10.3233\/FAIA190301"},{"key":"9425_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"9425_CR7","doi-asserted-by":"crossref","unstructured":"Curran JR, Clark S (2003) Language independent ner using a maximum entropy tagger. In: Daelemans, W., Osborne, M. (eds) Proceedings of CoNLL-2003. Edmonton, Canada","DOI":"10.3115\/1119176.1119200"},{"key":"9425_CR8","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). Association for Computational Linguistics,"},{"key":"9425_CR9","doi-asserted-by":"crossref","unstructured":"Fan Z, Wu Z, Dai X-Y, Huang S, Chen J (2019) Target-oriented opinion words extraction with target-fused neural sequence labeling. In: Proc. of NAACL 2019, pp. 2509\u20132518","DOI":"10.18653\/v1\/N19-1259"},{"key":"9425_CR10","doi-asserted-by":"crossref","unstructured":"Fox EA, Shaw JA (1993) Combination of multiple searches. In: Text Retrieval Conference","DOI":"10.6028\/NIST.SP.500-215.vt"},{"key":"9425_CR11","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200848","volume-title":"Retrieval of prior court cases using witness testimonies","author":"K Ghosh","year":"2020","unstructured":"Ghosh K, Pawar S, Palshikar G, Bhattacharyya P, Varma V (2020) Retrieval of prior court cases using witness testimonies. IOS Press, Legal Knowledge and Information Systems"},{"key":"9425_CR12","doi-asserted-by":"crossref","unstructured":"Hammerton J (2003) Named entity recognition with long short-term memory. In: Daelemans, W., Osborne, M. (eds.) Proceedings of CoNLL-2003. Edmonton, Canada","DOI":"10.3115\/1119176.1119202"},{"key":"9425_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34997-3_9","volume-title":"What Are Ontologies Good For?","author":"I Horrocks","year":"2013","unstructured":"Horrocks I (2013) What Are Ontologies Good For? Springer, Evolution of semantic systems"},{"key":"9425_CR14","unstructured":"Huang Z, Xu W, Yu K (2015) Bidirectional LSTM-CRF Models for Sequence Tagging"},{"key":"9425_CR15","unstructured":"Jensen KN, Plank B (2022) Fine-tuning vs from scratch: Do vision & language models have similar capabilities on out-of-distribution visual question answering? Proc. of LREC"},{"key":"9425_CR16","unstructured":"Kalim WB, Mercer RE (2022) Method entity extraction from biomedical texts. In: Proc. of the 29th International Conference on Computational Linguistics, pp. 2357\u20132362"},{"key":"9425_CR17","doi-asserted-by":"crossref","unstructured":"Kiyavitskaya N, Zeni N, Mich L, Cordy JR, Mylopoulos J (2006) Text mining through semi automatic semantic annotation. In: Practical Aspects of Knowledge Management: 6th International Conference, PAKM 2006, Vienna, Austria, November 30-December1, 2006. Proceedings 6, pp. 143\u2013154. Springer","DOI":"10.1007\/11944935_13"},{"key":"9425_CR18","doi-asserted-by":"crossref","unstructured":"Lavrenko V, Croft WB (2001) Relevance based language models. In: Proc. of SIGIR, pp. 120\u2013127","DOI":"10.1145\/383952.383972"},{"key":"9425_CR19","doi-asserted-by":"crossref","unstructured":"Liu Y, Fabbri AR, Liu P, Radev D, Cohan A (2023) On Learning to Summarize with Large Language Models as References","DOI":"10.18653\/v1\/2024.naacl-long.478"},{"key":"9425_CR20","unstructured":"Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2021) Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. CoRR"},{"key":"9425_CR21","doi-asserted-by":"crossref","unstructured":"Malik V, Sanjay R, Nigam SK, Ghosh K, Guha SK, Bhattacharya A, Modi A (2021) ILDC for CJPE: Indian legal documents corpus for court judgment prediction and explanation. Proc ACL, pp 4046\u20134062","DOI":"10.18653\/v1\/2021.acl-long.313"},{"key":"9425_CR22","doi-asserted-by":"crossref","unstructured":"Mandal A, Ghosh K, Ghosh S, Mandal S (2021) A sequence labeling model for catchphrase identification from legal case documents. Artificial Intelligence and Law, pp 1\u201334","DOI":"10.1007\/s10506-021-09296-2"},{"key":"9425_CR23","doi-asserted-by":"crossref","unstructured":"Mandal A, Ghosh K, Pal A, Ghosh S (2017) Automatic catchphrase identification from legal court case documents. In: Proc. of CIKM","DOI":"10.1145\/3132847.3133102"},{"issue":"2","key":"9425_CR24","first-page":"116","volume":"14","author":"K Munir","year":"2018","unstructured":"Munir K, Sheraz Anjum M (2018) The use of ontologies for effective knowledge modelling and information retrieval. Appl Comput Inf 14(2):116\u2013126","journal-title":"Appl Comput Inf"},{"key":"9425_CR25","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140389","author":"V Naik","year":"2023","unstructured":"Naik V, Patel P, Kannan R (2023) Legal entity extraction: an experimental study of ner approach for legal documents. Int J Adv Computer Sci Appl. https:\/\/doi.org\/10.14569\/IJACSA.2023.0140389","journal-title":"Int J Adv Computer Sci Appl"},{"key":"9425_CR26","doi-asserted-by":"crossref","unstructured":"Paul S, Mandal A, Goyal P, Ghosh S (2023) Pre-trained language models for the legal domain: a case study on indian law. In: Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law, pp. 187\u2013196","DOI":"10.1145\/3594536.3595165"},{"key":"9425_CR27","doi-asserted-by":"crossref","unstructured":"Paul S, Goyal P, Ghosh S (2020) Automatic charge identification from facts: A few sentence-level charge annotations is all you need. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 1011\u20131022","DOI":"10.18653\/v1\/2020.coling-main.88"},{"key":"9425_CR28","doi-asserted-by":"crossref","unstructured":"Podder RS, Bhattacharya P (2020) Unsupervised legal concept extraction from indian case documents using statutes. In: Proceedings of the 12th Annual Meeting of the Forum for Information Retrieval Evaluation, pp. 62\u201365","DOI":"10.1145\/3441501.3441508"},{"issue":"8","key":"9425_CR29","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"9425_CR30","doi-asserted-by":"crossref","unstructured":"Rei M, S\u00f8gaard A (2018) Zero-shot sequence labeling: Transferring knowledge from sentences to tokens. Proc.NAACL, pp. 293\u2013302","DOI":"10.18653\/v1\/N18-1027"},{"issue":"2","key":"9425_CR31","doi-asserted-by":"publisher","first-page":"375","DOI":"10.3390\/ai4020019","volume":"4","author":"P Rivas","year":"2023","unstructured":"Rivas P, Zhao L (2023) Marketing with chatgpt: Navigating the ethical terrain of gpt-based chatbot technology. AI 4(2):375\u2013384","journal-title":"AI"},{"key":"9425_CR32","doi-asserted-by":"crossref","unstructured":"Sari Y, Hassan MF, Zamin N (2010) Rule-based pattern extractor and named entity recognition: A hybrid approach. In: 2010 International Symposium on Information Technology, vol. 2, pp. 563\u2013568","DOI":"10.1109\/ITSIM.2010.5561392"},{"key":"9425_CR33","doi-asserted-by":"crossref","unstructured":"Shukla A, Bhattacharya P, Poddar S, Mukherjee R, Ghosh K, Goyal P, Ghosh S (2022) Legal case document summarization: Extractive and abstractive methods and their evaluation. In: Proc. of the 2nd Conference of the Asia-Pacific Chapter of the ACL and the 12th International Joint Conference on Natural Language Processing, Online only","DOI":"10.18653\/v1\/2022.aacl-main.77"},{"key":"9425_CR34","doi-asserted-by":"crossref","unstructured":"Sleimi A, Sannier N, Sabetzadeh M, Briand L, Dann J (2018) Automated extraction of semantic legal metadata using natural language processing. In: 2018 IEEE 26th International Requirements Engineering Conference (RE), pp. 124\u2013135. IEEE","DOI":"10.1109\/RE.2018.00022"},{"key":"9425_CR35","doi-asserted-by":"crossref","unstructured":"Strickson B, De\u00a0La\u00a0Iglesia B (2020) Legal judgement prediction for uk courts. In: Proceedings of the 3rd International Conference on Information Science and Systems, pp. 204\u2013209","DOI":"10.1145\/3388176.3388183"},{"key":"9425_CR37","unstructured":"Tran VD, Nguyen ML, Satoh K (2018) Automatic catchphrase extraction from legal case documents via scoring using deep neural networks. CoRR"},{"key":"9425_CR38","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) NEURIPS"},{"key":"9425_CR39","doi-asserted-by":"crossref","unstructured":"Vats S, Zope A, De S, Sharma A, Bhattacharya U, Nigam S, Guha S, Rudra K, Ghosh K (2023) Llms\u2013the good, the bad or the indispensable?: A use case on legal statute prediction and legal judgment prediction on indian court cases. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 12451\u201312474","DOI":"10.18653\/v1\/2023.findings-emnlp.831"},{"issue":"6","key":"9425_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103511","volume":"60","author":"Y Wang","year":"2023","unstructured":"Wang Y, Wang Y, Sun Z, Li Y, Hu S, Ye Y (2023) Deep purified feature mining model for joint named entity recognition and relation extraction. Inf Proce Manage 60(6):103511","journal-title":"Inf Proce Manage"},{"key":"9425_CR41","unstructured":"Wang S, Sun X, Li X, Ouyang R, Wu F, Zhang T, Li J, Wang G GPT-NER: Named Entity Recognition Via Large Language Models. arXiv preprint arXiv:2304.10428"},{"key":"9425_CR42","doi-asserted-by":"crossref","unstructured":"Wang H, Li J, Wu H, Hovy E, Sun Y (2022) Pre-trained language models and their applications. Engineering","DOI":"10.1016\/j.eng.2022.04.024"},{"key":"9425_CR43","volume-title":"Raise a child in large language model: Towards effective and generalizable fine-tuning","author":"R Xu","year":"2021","unstructured":"Xu R, Luo F, Zhang Z, Tan C, Chang B, Huang S, Huang F (2021) Raise a child in large language model: Towards effective and generalizable fine-tuning. Online and Punta Cana, Dominican Republic, Proc. of EMNLP"},{"key":"9425_CR44","doi-asserted-by":"crossref","unstructured":"Zhang X, Li D, Wu X (2014) Parsing named entity as syntactic structure. In: Interspeech. Fifteenth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2014-68"},{"key":"9425_CR45","unstructured":"Zhang B, Haddow B, Birch A (2023) Prompting Large Language Model for Machine Translation: A Case Study"}],"container-title":["Artificial Intelligence and Law"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-024-09425-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10506-024-09425-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-024-09425-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:45:21Z","timestamp":1774421121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10506-024-09425-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,11]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["9425"],"URL":"https:\/\/doi.org\/10.1007\/s10506-024-09425-7","relation":{},"ISSN":["0924-8463","1572-8382"],"issn-type":[{"value":"0924-8463","type":"print"},{"value":"1572-8382","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,11]]},"assertion":[{"value":"24 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}