{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:21:06Z","timestamp":1773415266729,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Digit. Gov.: Res. Pract."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Nowadays, workflows in judiciary systems are undergoing rapid transformation, stimulated by the technological opportunities offered by Generative AI solutions, including Large Language Models (LLMs). These technologies offer promising tools for addressing the inefficiencies and accessibility challenges inherent in traditional judicial workflows, which have long resisted digital modernization. By automating repetitive and time-intensive tasks such as text summarization and document analysis, LLMs can assist humans, thus enhancing operational effectiveness. This article presents an exploratory study conducted in the scope of a collaboration between researchers and IT experts from the University of Brescia and the Prosecutor General\u2019s Office at the Court of Appeal of Brescia. Adopting a Design Science Research methodology, the article describes the design and evaluation of a Proof-of-Concept Web application that leverages LLMs and prompt engineering to support text summarization and analysis tasks. The prototype is intended to assist legal professionals with domain expertise, but without advanced IT skills, in interacting effectively with Generative AI technologies. The study highlights the potential of LLMs to streamline human effort, reduce manual overhead, and support decision-making, while also pointing out key challenges for their adoption in judicial workflows.<\/jats:p>","DOI":"10.1145\/3785143","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T21:24:48Z","timestamp":1767129888000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Large Language Models in Judicial Workflows: Designing an LLM-based Crime Reporting Application through Design Science Research"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-3706","authenticated-orcid":false,"given":"Devis","family":"Bianchini","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Brescia","place":["Brescia, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5823-6595","authenticated-orcid":false,"given":"Massimiliano","family":"Garda","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Universit\u00e0 degli Studi di Brescia","place":["Brescia, Italy"]}]}],"member":"320","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"2023. Colombian judge says he used ChatGPT in ruling. The Guardian. Retrieved from https:\/\/www.theguardian.com\/technology\/2023\/feb\/03\/colombia-judge-chatgpt-ruling. Accessed on December 2024."},{"key":"e_1_3_3_3_2","unstructured":"2023. Court of appeal judge praises \u201cjolly useful\u201d ChatGPT after asking it for legal summary. The Guardian. Retrieved from https:\/\/www.theguardian.com\/technology\/2023\/sep\/15\/court-of-appeal-judge-praises-jolly-useful-chatgpt-after-asking-it-for-legal-summary. Accessed on December 2024."},{"key":"e_1_3_3_4_2","unstructured":"2024. AI in court a case study under the lens of the Artificial Intelligence Act. Retrieved from https:\/\/www.iusinitinere.it\/ai-in-court-a-case-study-under-the-lens-of-the-artificial-intelligence-act-42652. Accessed on December 2024."},{"key":"e_1_3_3_5_2","unstructured":"2024. Leveraging Large Language Models for Analyzing Judicial Disparities in China. Retrieved from https:\/\/dlab.berkeley.edu\/news\/leveraging-large-language-models-analyzing-judicial-disparities-china. Accessed on December 2024."},{"key":"e_1_3_3_6_2","unstructured":"2024. Prompt Chaining \u2013 Introduction and Use Cases. Retrieved from https:\/\/www.promptingguide.ai\/techniques\/prompt_chaining. Accessed on December 2024."},{"key":"e_1_3_3_7_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. GPT-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Irene Benedetto Moreno La Quatra and Luca Cagliero. 2025. LegItBART: A summarization model for Italian legal documents. Artificial Intelligence and Law (2025) 1\u201331.","DOI":"10.1007\/s10506-025-09436-y"},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Devis Bianchini Carlo Bono Alessandro Campi Cinzia Cappiello Stefano Ceri Francesca De Luzi Massimo Mecella Barbara Pernici and Pierluigi Plebani. 2024. Challenges in AI-supported process analysis in the Italian judicial system: What after digitalization? Digital Government: Research and Practice 5 1 (2024) 1\u201310.","DOI":"10.1145\/3630025"},{"key":"e_1_3_3_11_2","unstructured":"David M. Blei Andrew Y. Ng and Michael I. Jordan. 2003. Latent dirichlet allocation. Journal of Machine Learning Research 3 Jan (2003) 993\u20131022."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230641"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.36745\/ijca.604"},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Pratim Milton Datta and Thomas et\u00a0al. Acton. 2023. GiusBERTo: Italy\u2019s AI-based judicial transformation: A teaching case. Communications of the Association for Information Systems 53 1 (2023) 751\u2013766.","DOI":"10.17705\/1CAIS.05331"},{"key":"e_1_3_3_15_2","unstructured":"DBMDZ. 2024. BERT Base Italian XXL Cased. Retrieved from https:\/\/huggingface.co\/dbmdz\/bert-base-italian-xxl-cased. Accessed: 2024-03-11."},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Petrus M. J. Delport Rossouw Von Solms and Mariana Gerber. 2024. Methodological guidelines for design science research. Procedia Computer Science 237 C (2024) 195\u2013203.","DOI":"10.1016\/j.procs.2024.05.096"},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Anna-Katharina Dhungel. 2025. \u201cThis verdict was created with the help of generative AI...?\u201d On the use of large language models by judges. Digital Government: Research and Practice 6 1 (2025) 1\u20138.","DOI":"10.1145\/3696319"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1002\/0471741442"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Alexander R. Fabbri Wojciech Kry\u015bci\u0144ski Bryan McCann Caiming Xiong Richard Socher and Dragomir Radev. 2021. SummEval: Re-evaluating summarization evaluation. Transactions of the Association for Computational Linguistics 9 (2021) 391\u2013409.","DOI":"10.1162\/tacl_a_00373"},{"key":"e_1_3_3_20_2","unstructured":"Frank Fagan. 2024. A view of how language models will transform law. arXiv:2405.07826. Retrieved from https:\/\/arxiv.org\/abs\/2405.07826"},{"key":"e_1_3_3_21_2","unstructured":"Yunfan Gao et\u00a0al. 2023. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997. Retrieved from https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.4337\/9781803922171.00033"},{"key":"e_1_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Alan R. Hevner Salvatore T. March Jinsoo Park and Sudha Ram. 2004. Design science in information systems research. MIS Quarterly 28 1 (2004) 75\u2013105.","DOI":"10.2307\/25148625"},{"key":"e_1_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Ankur Joshi Saket Kale Satish Chandel and D. Kumar Pal. 2015. Likert scale: Explored and explained. British Journal of Applied Science & Technology 7 4 (2015) 396\u2013403.","DOI":"10.9734\/BJAST\/2015\/14975"},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Jinqi Lai Wensheng Gan Jiayang Wu Zhenlian Qi and S. Yu Philip. 2024. Large language models in law: A survey. AI Open 5 (2024) 181\u2013196.","DOI":"10.1016\/j.aiopen.2024.09.002"},{"key":"e_1_3_3_26_2","volume-title":"Open Source Strikes Bread - New Fluffy Embeddings Model","author":"Lee Sean","year":"2024","unstructured":"Sean Lee, Aamir Shakir, Darius Koenig, and Julius Lipp. 2024. Open Source Strikes Bread - New Fluffy Embeddings Model. Retrieved from https:\/\/www.mixedbread.ai\/blog\/mxbai-embed-large-v1"},{"key":"e_1_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Daniele Licari and Giovanni Comand\u00e8. 2024. Italian-Legal-Bert models for improving natural language processing tasks in the Italian legal domain. Computer Law & Security Review 52 (2024) 105908.","DOI":"10.1016\/j.clsr.2023.105908"},{"key":"e_1_3_3_28_2","first-page":"74","volume-title":"Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text Summarization Branches Out. 74\u201381."},{"key":"e_1_3_3_29_2","volume-title":"REST API Design Rulebook","author":"Masse Mark","year":"2011","unstructured":"Mark Masse. 2011. REST API Design Rulebook. \u201cO\u2019Reilly Media, Inc.\u201d."},{"key":"e_1_3_3_30_2","unstructured":"Ministero della Giustizia. 2011. The General Prosecution Office at the Italian Supreme Court. Retrieved from https:\/\/www.giustizia.it\/giustizia\/it\/mg_2_1_4_2_2.wp. Accessed: 2024-12-14."},{"key":"e_1_3_3_31_2","unstructured":"OpenAI. 2024. How your data is used to improve model performance. Retrieved from https:\/\/help.openai.com\/en\/articles\/5722486-how-your-data-is-used-to-improve-model-performance. Accessed: 2024-03-11."},{"key":"e_1_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Bogdan Padiu Radu Iacob Traian Rebedea and Mihai Dascalu. 2024. To what extent have LLMs reshaped the legal domain so far? a scoping literature review. Information 15 11 (2024) 662.","DOI":"10.3390\/info15110662"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Ajay Patel Delip Rao Ansh Kothary Kathleen McKeown and Chris Callison-Burch. 2023. Learning interpretable style embeddings via prompting LLMs. arXiv:2305.12696. Retrieved from https:\/\/arxiv.org\/abs\/2305.12696","DOI":"10.18653\/v1\/2023.findings-emnlp.1020"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Ken Peffers Tuure Tuunanen Marcus A. Rothenberger and Samir Chatterjee. 2007. A design science research methodology for information systems research. Journal of Management Information Systems 24 3 (2007) 45\u201377.","DOI":"10.2753\/MIS0742-1222240302"},{"key":"e_1_3_3_35_2","unstructured":"Weicong Qin and Zhongxiang Sun. 2024. Exploring the nexus of large language models and legal systems: A short survey. arXiv:2404.00990. Retrieved from https:\/\/arxiv.org\/abs\/2404.00990"},{"key":"e_1_3_3_36_2","unstructured":"Pranab Sahoo Ayush Kumar Singh Sriparna Saha Vinija Jain Samrat Mondal and Aman Chadha. 2024. A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv:2402.07927 (2024)."},{"key":"e_1_3_3_37_2","unstructured":"Giulio Salierno Rosamaria Bert\u00e8 Luca Attias Carla Morrone Dario Pettazzoni and Daniela Battisti. 2024. GiusBERTo: A legal language model for personal data de-identification in Italian court of auditors decisions. arXiv:2402.07927. Retrieved from https:\/\/arxiv.org\/abs\/2402.07927"},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Andrea Tagarelli and Andrea Simeri. 2022. Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code. Artificial Intelligence and Law 30 3 (2022) 417\u2013473.","DOI":"10.1007\/s10506-021-09301-8"},{"key":"e_1_3_3_39_2","unstructured":"Kassym-Jomart Tokayev. 2023. Ethical implications of large language models a multidimensional exploration of societal economic and technical concerns. International Journal of Social Analytics 8 9 (2023) 17\u201333."},{"key":"e_1_3_3_40_2","unstructured":"Sentence Transformers. 2024. sentence-transformers\/paraphrase-multilingual-MiniLM-L12-v2: A Sentence Transformer Model. Retrieved from https:\/\/huggingface.co\/sentence-transformers\/paraphrase-multilingual-MiniLM-L12-v2. Accessed: 2024-03-11."},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Wil Van Der Aalst. 2012. Process mining: Overview and opportunities. ACM Transactions on Management Information Systems (TMIS) 3 2 (2012) 1\u201317.","DOI":"10.1145\/2229156.2229157"},{"key":"e_1_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Bin Wang Angela Wang Fenxiao Chen Yuncheng Wang and C.-C. Jay Kuo. 2019. Evaluating word embedding models: Methods and experimental results. APSIPA Transactions on Signal and Information Processing 8 (2019) e19.","DOI":"10.1017\/ATSIP.2019.12"},{"key":"e_1_3_3_43_2","unstructured":"Yufei Wang Wanjun Zhong Liangyou Li Fei Mi Xingshan Zeng Wenyong Huang Lifeng Shang Xin Jiang and Qun Liu. 2023. Aligning large language models with human: A survey. arXiv preprint arXiv:2307.12966 (2023)."},{"key":"e_1_3_3_44_2","unstructured":"Hannes Westermann Jaromir Savelka and Karim Benyekhlef. 2023. Llmediator: Gpt-4 assisted online dispute resolution. arXiv:2307.12966. Retrieved from https:\/\/arxiv.org\/abs\/2307.12966"},{"key":"e_1_3_3_45_2","unstructured":"Jules White Quchen Fu Sam Hays Michael Sandborn Carlos Olea Henry Gilbert Ashraf Elnashar Jesse Spencer-Smith and Douglas C. Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv:2302.11382. Retrieved from https:\/\/arxiv.org\/abs\/2302.11382"},{"key":"e_1_3_3_46_2","unstructured":"Haoran Yang Yumeng Zhang Jiaqi Xu Hongyuan Lu Pheng Ann Heng and Wai Lam. 2024. Unveiling the generalization power of fine-tuned large language models. arXiv:2403.09162. Retrieved from https:\/\/arxiv.org\/abs\/2403.09162"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Collin Zhang John X. Morris and Vitaly Shmatikov. 2024. Extracting prompts by inverting LLM outputs. arXiv:2405.15012. Retrieved from https:\/\/arxiv.org\/abs\/2405.15012","DOI":"10.18653\/v1\/2024.emnlp-main.819"},{"key":"e_1_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et\u00a0al. 2024. Judging LLM-as-a-judge with MT-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2024) 46595\u201346623.","DOI":"10.52202\/075280-2020"}],"container-title":["Digital Government: Research and Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3785143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T11:41:47Z","timestamp":1773402107000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3785143"],"URL":"https:\/\/doi.org\/10.1145\/3785143","relation":{},"ISSN":["2691-199X","2639-0175"],"issn-type":[{"value":"2691-199X","type":"print"},{"value":"2639-0175","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"assertion":[{"value":"2025-03-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}