{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:46:01Z","timestamp":1769165161061,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":91,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3696630.3728530","type":"proceedings-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:08:09Z","timestamp":1753729689000},"page":"39-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8779-3116","authenticated-orcid":false,"given":"Jingwen","family":"Tan","sequence":"first","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1812-5365","authenticated-orcid":false,"given":"Gopi Krishnan","family":"Rajbahadur","sequence":"additional","affiliation":[{"name":"Centre for Software Excellence, Huawei, Canada, Ottawa, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9105-0516","authenticated-orcid":false,"given":"Zi","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei China, shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5134-4233","authenticated-orcid":false,"given":"Xiangfu","family":"Song","sequence":"additional","affiliation":[{"name":"Centre for Software Excellence, Huawei, Canada, Ottawa, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5680-8312","authenticated-orcid":false,"given":"Jianshan","family":"Lin","sequence":"additional","affiliation":[{"name":"Huawei China, shenzhen, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3787-1673","authenticated-orcid":false,"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7878-4330","authenticated-orcid":false,"given":"Zibin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7749-5513","authenticated-orcid":false,"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[{"name":"Queen's University, Kingston, Canada"}]}],"member":"320","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Lexilaw. [Online]. Available: https:\/\/github.com\/CSHaitao\/LexiLaw"},{"key":"e_1_3_2_1_2_1","unstructured":"wisdominterrogatory. [Online]. Available: https:\/\/github.com\/zhihaiLLM\/wisdomInterrogatory"},{"key":"e_1_3_2_1_3_1","first-page":"1381","volume-title":"katzer","year":"2008","unstructured":"\"Jacobsen v. katzer,\" pp. 1373\u20131381, 2008."},{"key":"e_1_3_2_1_4_1","unstructured":"\"Open data commons public domain dedication and license (pddl) \" 2018 open Data Commons License. [Online]. Available: https:\/\/opendatacommons.org\/licenses\/pddl\/"},{"key":"e_1_3_2_1_5_1","unstructured":"\"Amazon s3 \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/aws.amazon.com\/s3\/"},{"key":"e_1_3_2_1_6_1","unstructured":"\"Datahub \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/datahub.io\/"},{"key":"e_1_3_2_1_7_1","unstructured":"\"Figshare \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/figshare.com\/"},{"key":"e_1_3_2_1_8_1","unstructured":"\"Github \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/github.com\/"},{"key":"e_1_3_2_1_9_1","unstructured":"\"Gitlab \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/gitlab.com\/"},{"key":"e_1_3_2_1_10_1","unstructured":"\"Google cloud \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/cloud.google.com\/"},{"key":"e_1_3_2_1_11_1","unstructured":"\"Hugging face \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/huggingface.co\/"},{"key":"e_1_3_2_1_12_1","unstructured":"\"Kaggle \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/www.kaggle.com\/"},{"key":"e_1_3_2_1_13_1","unstructured":"\"Microsoft azure \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/azure.microsoft.com\/"},{"key":"e_1_3_2_1_14_1","unstructured":"\"Opendataology \" 2023 accessed: 2024-10-02. [Online]. Available: http:\/\/www.opendataology.com:30800\/#\/dataSetAll"},{"key":"e_1_3_2_1_15_1","unstructured":"\"SPDX 3.0 Dataset Profile \" 2023 accessed: 2024-10-11. [Online]. Available: https:\/\/spdx.github.io\/spdx-spec\/v3.0\/model\/Dataset\/Dataset\/"},{"key":"e_1_3_2_1_16_1","unstructured":"\"Zenodo \" 2023 accessed: 2024-10-02. [Online]. Available: https:\/\/zenodo.org\/"},{"key":"e_1_3_2_1_17_1","unstructured":"\"Github licensing guide \" 2024 https:\/\/docs.github.com\/en\/repositories\/managing-your-repositorys-settings-and-features\/customizing-your-repository\/licensing-a-repository."},{"key":"e_1_3_2_1_18_1","unstructured":"\"Open source initiative \" 2024 available at: https:\/\/opensource.org\/licenses."},{"key":"e_1_3_2_1_19_1","unstructured":"\"SPDX AI - Areas of Interest \" 2024 accessed: 2024-10-11. [Online]. Available: https:\/\/spdx.dev\/learn\/areas-of-interest\/ai\/"},{"key":"e_1_3_2_1_20_1","volume-title":"Understand open source licenses","year":"2024","unstructured":"\"Tldrlegal: Understand open source licenses,\" 2024, available at: https:\/\/www.tldrlegal.com\/."},{"key":"e_1_3_2_1_21_1","volume-title":"Open-source pretrained large-scale language model,\" https:\/\/modelscope.cn\/models\/damo","author":"A. D. Academy","year":"2023","unstructured":"A. D. Academy, \"Qwen: Open-source pretrained large-scale language model,\" https:\/\/modelscope.cn\/models\/damo, 2023, accessed: 2024-10-04."},{"key":"e_1_3_2_1_22_1","volume-title":"Open and efficient foundation language models,\" https:\/\/ai.meta.com\/llama","author":"M. AI","year":"2023","unstructured":"M. AI, \"Llama-2: Open and efficient foundation language models,\" https:\/\/ai.meta.com\/llama, 2023, accessed: 2024-10-04."},{"key":"e_1_3_2_1_23_1","volume-title":"What, how, and why it matters for nlp","author":"N. AI","year":"2023","unstructured":"N. AI, \"Zero-shot learning: What, how, and why it matters for nlp,\" 2023, accessed: 2024-10-05. [Online]. Available: https:\/\/neptune.ai\/blog\/zero-shot-learning"},{"key":"e_1_3_2_1_24_1","first-page":"300","volume-title":"IEEE","author":"Amershi S.","year":"2019","unstructured":"S. Amershi, A. Begel, C. Bird, R. DeLine, H. Gall, E. Kamar, N. Nagappan, B. Nushi, and T. Zimmermann, \"Software engineering for machine learning: A case study,\" in 2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 2019, pp. 291\u2013300."},{"issue":"4","key":"e_1_3_2_1_25_1","first-page":"6","article-title":"Factsheets: Increasing trust in ai services through supplier's declarations of conformity","volume":"63","author":"Arnold M.","year":"2019","unstructured":"M. Arnold, R. K. Bellamy, M. Hind, S. Houde, S. Mehta, A. Mojsilovi\u0107, R. Nair, K. N. Ramamurthy, A. Olteanu, D. Piorkowski et al., \"Factsheets: Increasing trust in ai services through supplier's declarations of conformity,\" IBM Journal of Research and Development, vol. 63, no. 4\/5, pp. 6\u20131, 2019.","journal-title":"IBM Journal of Research and Development"},{"key":"e_1_3_2_1_26_1","volume-title":"Promptsource: An integrated development environment and repository for natural language prompts","author":"Bach S. H.","year":"2022","unstructured":"S. H. Bach et al., \"Promptsource: An integrated development environment and repository for natural language prompts,\" 2022."},{"key":"e_1_3_2_1_27_1","volume-title":"Towards traceability in data ecosystems using a bill of materials model,\" arXiv preprint arXiv:1904.04253","author":"Barclay I.","year":"2019","unstructured":"I. Barclay, A. Preece, I. Taylor, and D. Verma, \"Towards traceability in data ecosystems using a bill of materials model,\" arXiv preprint arXiv:1904.04253, 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"Towards standardization of data licenses: The montreal data license,\" arXiv preprint arXiv:1903.12262","author":"Benjamin M.","year":"2019","unstructured":"M. Benjamin, P. Gagnon, N. Rostamzadeh, C. Pal, Y. Bengio, and A. Shee, \"Towards standardization of data licenses: The montreal data license,\" arXiv preprint arXiv:1903.12262, 2019."},{"key":"e_1_3_2_1_29_1","volume-title":"Chatgpt-4 performance on legal benchmarks: Evaluating its applicability for specialized tasks,\" Artificial Intelligence and Law","author":"Bommarito M.","year":"2023","unstructured":"M. Bommarito and D. Katz, \"Chatgpt-4 performance on legal benchmarks: Evaluating its applicability for specialized tasks,\" Artificial Intelligence and Law, 2023. [Online]. Available: https:\/\/link.springer.com\/article\/10.1007\/s10506-023-09356-y"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Breaux et al. \"Analyzing regulatory rules for privacy and security requirements \" IEEE Transactions on Software Engineering 2008.","DOI":"10.1109\/TSE.2007.70746"},{"key":"e_1_3_2_1_31_1","first-page":"1901","volume-title":"Askell et al., \"Language models are few-shot learners,\" Advances in neural information processing systems","author":"Brown T.","year":"2020","unstructured":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., \"Language models are few-shot learners,\" Advances in neural information processing systems, vol. 33, pp. 1877\u20131901, 2020."},{"key":"e_1_3_2_1_32_1","first-page":"358","article-title":"Objectives and key results in software teams: Challenges, opportunities and impact on development,\" in Proceedings of the 46th International Conference on Software Engineering","author":"Butler J. L.","year":"2024","unstructured":"J. L. Butler, T. Zimmermann, and C. Bird, \"Objectives and key results in software teams: Challenges, opportunities and impact on development,\" in Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice, 2024, pp. 358\u2013368.","journal-title":"Software Engineering in Practice"},{"key":"e_1_3_2_1_33_1","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen J.","year":"1988","unstructured":"J. Cohen, Statistical Power Analysis for the Behavioral Sciences, 2nd ed. Hillsdale, NJ: Lawrence Erlbaum Associates, 1988.","edition":"2"},{"key":"e_1_3_2_1_34_1","unstructured":"C. Commons \"Creative commons attribution license (cc by) \" 2013 creative Commons License. [Online]. Available: https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"key":"e_1_3_2_1_35_1","volume-title":"Chatlaw: Open-source legal large language model with integrated external knowledge bases,\" arXiv preprint arXiv:2306.16092","author":"Cui J.","year":"2023","unstructured":"J. Cui, Z. Li, Y. Yan, B. Chen, and L. Yuan, \"Chatlaw: Open-source legal large language model with integrated external knowledge bases,\" arXiv preprint arXiv:2306.16092, 2023."},{"key":"e_1_3_2_1_36_1","volume-title":"Efficient and effective text encoding for chinese llama and alpaca,\" arXiv preprint arXiv:2304.08177","author":"Cui Y.","year":"2023","unstructured":"Y. Cui, Z. Yang, and X. Yao, \"Efficient and effective text encoding for chinese llama and alpaca,\" arXiv preprint arXiv:2304.08177, 2023."},{"key":"e_1_3_2_1_37_1","first-page":"320","article-title":"Glm: General language model pretraining with autoregressive blank infilling,\" in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1","author":"Du Z.","year":"2022","unstructured":"Z. Du, Y. Qian, X. Liu, M. Ding, J. Qiu, Z. Yang, and J. Tang, \"Glm: General language model pretraining with autoregressive blank infilling,\" in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 320\u2013335.","journal-title":"Long Papers)"},{"issue":"293","key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1080\/01621459.1961.10482090","article-title":"Multiple comparisons among means","volume":"56","author":"Dunn O. J.","year":"1961","unstructured":"O. J. Dunn, \"Multiple comparisons among means,\" Journal of the American statistical association, vol. 56, no. 293, pp. 52\u201364, 1961.","journal-title":"Journal of the American statistical association"},{"key":"e_1_3_2_1_39_1","unstructured":"H. Face \"What is zero-shot classification?\" 2023 accessed: 2024-10-05. [Online]. Available: https:\/\/huggingface.co\/docs\/transformers\/main\/en\/task_summary#zero-shot-classification"},{"issue":"12","key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/3458723","article-title":"Datasheets for datasets","volume":"64","author":"Gebru T.","year":"2021","unstructured":"T. Gebru, J. Morgenstern, B. Vecchione, J. W. Vaughan, H. Wallach, H. D. Iii, and K. Crawford, \"Datasheets for datasets,\" Communications of the ACM, vol. 64, no. 12, pp. 86\u201392, 2021.","journal-title":"Communications of the ACM"},{"issue":"3","key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/MS.2012.50","article-title":"A method for open source license compliance of java applications","volume":"29","author":"German D.","year":"2012","unstructured":"D. German and M. Di Penta, \"A method for open source license compliance of java applications,\" IEEE software, vol. 29, no. 3, pp. 58\u201363, 2012.","journal-title":"IEEE software"},{"key":"e_1_3_2_1_42_1","first-page":"198","volume-title":"IEEE","author":"German D. M.","year":"2009","unstructured":"D. M. German and A. E. Hassan, \"License integration patterns: Addressing license mismatches in component-based development,\" in 2009 IEEE 31st international conference on software engineering. IEEE, 2009, pp. 188\u2013198."},{"key":"e_1_3_2_1_43_1","volume-title":"The legal aspects of licensing for commercial purposes","year":"2023","unstructured":"GetInData, \"Large language models: The legal aspects of licensing for commercial purposes,\" 2023, accessed: 2024-10-02. [Online]. Available: https:\/\/getindata.com\/blog\/large-language-models-legal-aspects-licensing-commercial-purposes\/"},{"key":"e_1_3_2_1_44_1","volume-title":"Your ai pair programmer,\" https:\/\/copilot.github.com","year":"2021","unstructured":"GitHub, \"Github copilot: Your ai pair programmer,\" https:\/\/copilot.github.com, 2021, accessed: 2024-07-03."},{"key":"e_1_3_2_1_45_1","unstructured":"Government of Canada \"Infringement of copyright and moral rights and exceptions to infringement (continued) \" 2021 [Last visited on 09-25-2024]. [Online]. Available: https:\/\/laws-lois.justice.gc.ca\/eng\/acts\/c-42\/page-9.html"},{"key":"e_1_3_2_1_46_1","first-page":"44","volume-title":"A. Oh","author":"Guha N.","year":"2023","unstructured":"N. Guha, Nyarko et al., \"Legalbench: A collaboratively built benchmark for measuring legal reasoning in large language models,\" in Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, Eds., vol. 36. Curran Associates, Inc., 2023, pp. 44 123\u201344 279. [Online]. Available: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/89e44582fd28ddfea1ea4dcb0ebbf4b0-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_47_1","first-page":"62","volume-title":"Fossology: A license compliance tool,\" in IFIP International Conference on Open Source Systems","author":"Hansen F.","year":"2010","unstructured":"F. Hansen, B. Becker, C. Chamas, and P. Germain, \"Fossology: A license compliance tool,\" in IFIP International Conference on Open Source Systems. Springer, 2010, pp. 47\u201362."},{"key":"e_1_3_2_1_48_1","unstructured":"Harvard Gazette \"Key issues in writers' case against openai explained \" Sep. 2023. [Online]. Available: https:\/\/news.harvard.edu\/gazette\/story\/2023\/09\/key-issues-in-writers-case-against-openai-explained\/"},{"key":"e_1_3_2_1_49_1","volume-title":"Ming et al., \"Rethinking software engineering in the foundation model era: From task-driven ai copilots to goal-driven ai pair programmers,\" arXiv preprint arXiv:2404.10225","author":"Hassan A. E.","year":"2024","unstructured":"A. E. Hassan, G. A. Oliva, D. Lin, B. Chen, Z. Ming et al., \"Rethinking software engineering in the foundation model era: From task-driven ai copilots to goal-driven ai pair programmers,\" arXiv preprint arXiv:2404.10225, 2024."},{"key":"e_1_3_2_1_50_1","volume-title":"Lawyer llama technical report,\" arXiv preprint arXiv:2305.15062","author":"Huang Q.","year":"2023","unstructured":"Q. Huang, M. Tao, Z. An, C. Zhang, C. Jiang, Z. Chen, Z. Wu, and Y. Feng, \"Lawyer llama technical report,\" arXiv preprint arXiv:2305.15062, 2023."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.datak.2012.12.004","article-title":"Arguing regulatory compliance of software requirements","volume":"87","author":"Ingolfo S.","year":"2013","unstructured":"S. Ingolfo, A. Siena, J. Mylopoulos, A. Susi, and A. Perini, \"Arguing regulatory compliance of software requirements,\" Data & Knowledge Engineering, vol. 87, pp. 279\u2013296, 2013.","journal-title":"Data & Knowledge Engineering"},{"issue":"2","key":"e_1_3_2_1_52_1","first-page":"153","article-title":"Fossology: The open source license compliance tool","volume":"1","author":"Jaeger M. C.","year":"2009","unstructured":"M. C. Jaeger, G. J. Herzwurm, and J. B\u00f6hm, \"Fossology: The open source license compliance tool,\" International Free and Open Source Software Law Review, vol. 1, no. 2, pp. 153\u2013171, 2009.","journal-title":"International Free and Open Source Software Law Review"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.jss.2016.06.064","article-title":"Automating the license compatibility process in open source software with spdx","volume":"131","author":"Kapitsaki G. M.","year":"2017","unstructured":"G. M. Kapitsaki, F. Kramer, and N. D. Tselikas, \"Automating the license compatibility process in open source software with spdx,\" Journal of systems and software, vol. 131, pp. 386\u2013401, 2017.","journal-title":"Journal of systems and software"},{"key":"e_1_3_2_1_54_1","volume-title":"Barcelona, Spain, October 20\u201324","author":"Kiyavitskaya N.","year":"2008","unstructured":"N. Kiyavitskaya, N. Zeni, T. D. Breaux, A. I. Ant 'on, J. R. Cordy, L. Mich, and J. Mylopoulos, \"Automating the extraction of rights and obligations for regulatory compliance,\" in Proceedings of the 27th International Conference on Conceptual Modeling, Barcelona, Spain, October 20\u201324, 2008."},{"key":"e_1_3_2_1_55_1","first-page":"231","article-title":"Enforcing the gpl and open source software licenses in the us after jacobsen v. katzer","volume":"27","author":"Kuhn B. M.","year":"2012","unstructured":"B. M. Kuhn and K. M. Sandler, \"Enforcing the gpl and open source software licenses in the us after jacobsen v. katzer,\" Berkeley Technology Law Journal, vol. 27, pp. 231\u2013274, 2012.","journal-title":"Berkeley Technology Law Journal"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"C.-H. Lin and P.-J. Cheng \"Legal documents drafting with fine-tuned pre-trained large language model \" arXiv preprint arXiv:2406.04202 2024.","DOI":"10.5121\/csit.2024.140819"},{"key":"e_1_3_2_1_57_1","unstructured":"M. LiuHongcheng LiaoYusheng and WangYuhao \"Lawgpt:chinese legal model \" 2023. [Online]. Available: https:\/\/github.com\/LiuHC0428\/LAW_GPT"},{"key":"e_1_3_2_1_58_1","volume-title":"Perisetla et al., \"The data provenance initiative: A large scale audit of dataset licensing & attribution in ai,\" arXiv preprint arXiv:2310.16787","author":"Longpre S.","year":"2023","unstructured":"S. Longpre, R. Mahari, A. Chen, N. Obeng-Marnu, D. Sileo, W. Brannon, N. Muennighoff, N. Khazam, J. Kabbara, K. Perisetla et al., \"The data provenance initiative: A large scale audit of dataset licensing & attribution in ai,\" arXiv preprint arXiv:2310.16787, 2023."},{"key":"e_1_3_2_1_59_1","first-page":"229","volume-title":"Model cards for model reporting,\" in Proceedings of the conference on fairness, accountability, and transparency","author":"Mitchell M.","year":"2019","unstructured":"M. Mitchell, S. Wu, A. Zaldivar, P. Barnes, L. Vasserman, B. Hutchinson, E. Spitzer, I. D. Raji, and T. Gebru, \"Model cards for model reporting,\" in Proceedings of the conference on fairness, accountability, and transparency, 2019, pp. 220\u2013229."},{"issue":"1","key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MITP.2020.3019961","article-title":"The rise of open source program office","volume":"23","author":"Munir H.","year":"2021","unstructured":"H. Munir and C.-E. Mols, \"The rise of open source program office,\" IT Professional, vol. 23, no. 1, pp. 27\u201333, 2021.","journal-title":"IT Professional"},{"key":"e_1_3_2_1_61_1","volume-title":"of Canada, \"A guide to copyright","author":"G.","year":"2021","unstructured":"G. of Canada, \"A guide to copyright,\" 2021, [Last visited on 09-25-2024]. [Online]. Available: https:\/\/laws-lois.justice.gc.ca\/eng\/acts\/c-42\/page-9.html"},{"key":"e_1_3_2_1_62_1","unstructured":"U. C. Office \"More information on fair use \" 2021 [Last visited on 09-25-2024]. [Online]. Available: https:\/\/www.copyright.gov\/fair-use\/more-info.html"},{"key":"e_1_3_2_1_63_1","unstructured":"OpenAI \"Gpt-4 \" https:\/\/openai.com\/gpt-4 2023 accessed: 2024-10-04."},{"key":"e_1_3_2_1_64_1","volume-title":"Full Recording,\" https:\/\/openchainproject.org\/news\/2024\/04\/09\/openchain-ai-study-group-monthly-workshop-for-north-\/america-and-europe-2024-04-02-full-recording","author":"\"OpenChain AI Study Group Monthly Workshop for North America and Europe","year":"2024","unstructured":"OpenChain Project, \"OpenChain AI Study Group Monthly Workshop for North America and Europe: Full Recording,\" https:\/\/openchainproject.org\/news\/2024\/04\/09\/openchain-ai-study-group-monthly-workshop-for-north-\/america-and-europe-2024-04-02-full-recording, 2024, last accessed: October 10, 2024."},{"key":"e_1_3_2_1_65_1","unstructured":"\"Openchain project \" https:\/\/openchainproject.org\/ OpenChain Project 2024 accessed: 2024-10-10."},{"key":"e_1_3_2_1_66_1","unstructured":"OpenDataology \"LicenseGPT \" https:\/\/github.com\/OpenDataology\/LicenseGPT 2024 gitHub repository Last accessed: 2024-10-11."},{"issue":"5","key":"e_1_3_2_1_67_1","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.3390\/app14052074","article-title":"A review of current trends, techniques, and challenges in large language models (llms)","volume":"14","author":"Patil R.","year":"2024","unstructured":"R. Patil and V. Gudivada, \"A review of current trends, techniques, and challenges in large language models (llms),\" Applied Sciences, vol. 14, no. 5, p. 2074, 2024.","journal-title":"Applied Sciences"},{"key":"e_1_3_2_1_68_1","volume-title":"Mitigating dataset harms requires stewardship: Lessons from 1000 papers,\" arXiv preprint arXiv:2108.02922","author":"Peng K.","year":"2021","unstructured":"K. Peng, A. Mathur, and A. Narayanan, \"Mitigating dataset harms requires stewardship: Lessons from 1000 papers,\" arXiv preprint arXiv:2108.02922, 2021."},{"key":"e_1_3_2_1_69_1","first-page":"1","article-title":"Can i use this publicly available dataset to build commercial ai software? most likely not","volume":"02374","author":"Rajbahadur G. K.","year":"2021","unstructured":"G. K. Rajbahadur, E. Tuck, L. Zi, Z. Wei, D. Lin, B. Chen, Z. M. Jiang, and D. M. German, \"Can i use this publicly available dataset to build commercial ai software? most likely not,\" CoRR, abs\/2111.02374, pp. 1\u20131, 2021.","journal-title":"CoRR, abs\/2111"},{"key":"e_1_3_2_1_70_1","unstructured":"T. Researcher \"Self-reflective chain-of-thought reasoning in large language models \" 2023."},{"key":"e_1_3_2_1_71_1","volume-title":"Open source software: Risks, compliance, and best practices. [Online]. Available: https:\/\/www.wsgr.com\/en\/insights\/open-source-software-risks-compliance-and-best-practices.html","author":"Rosati W. S.","year":"2017","unstructured":"W. S. G.. Rosati. (2017) Open source software: Risks, compliance, and best practices. [Online]. Available: https:\/\/www.wsgr.com\/en\/insights\/open-source-software-risks-compliance-and-best-practices.html"},{"key":"e_1_3_2_1_72_1","volume-title":"Simultaneous statistical inference","author":"Rupert G.","year":"2012","unstructured":"G. Rupert Jr et al., \"Simultaneous statistical inference,\" 2012."},{"key":"e_1_3_2_1_73_1","volume-title":"Zhongkun Liu et al., \"fuzi.mingcha","author":"Shiguang Wu Z. Z.","year":"2023","unstructured":"Z. Z. Shiguang Wu, Zhongkun Liu et al., \"fuzi.mingcha,\" 2023. [Online]. Available: https:\/\/github.com\/irlab-sdu\/fuzi.mingcha"},{"key":"e_1_3_2_1_74_1","volume-title":"Open source security and license compliance management. [Online]. Available: https:\/\/www.blackducksoftware.com","author":"Software B. D.","year":"2023","unstructured":"B. D. Software. (2023) Open source security and license compliance management. [Online]. Available: https:\/\/www.blackducksoftware.com"},{"key":"e_1_3_2_1_75_1","volume-title":"Chinese-llama tuned with chinese legal knowledge","author":"Song Pengxiao Z. Z.","year":"2023","unstructured":"Z. Z. Song Pengxiao and cainiao, \"Lawgpt: Chinese-llama tuned with chinese legal knowledge,\" 2023. [Online]. Available: https:\/\/github.com\/pengxiao-song\/LaWGPT"},{"issue":"2","key":"e_1_3_2_1_76_1","first-page":"178","article-title":"Responsible ai licenses-a real alternative to generally applicable laws?","volume":"1","author":"Szpyt K.","year":"2020","unstructured":"K. Szpyt, \"Responsible ai licenses-a real alternative to generally applicable laws?\" Revista Ib\u00e9rica do Direito, vol. 1, no. 2, pp. 178\u2013186, 2020.","journal-title":"Revista Ib\u00e9rica do Direito"},{"key":"e_1_3_2_1_77_1","article-title":"The impact of automated parameter optimization for defect prediction models","author":"Tantithamthavorn C.","year":"2018","unstructured":"C. Tantithamthavorn, S. McIntosh, A. E. Hassan, and K. Matsumoto, \"The impact of automated parameter optimization for defect prediction models,\" IEEE Transactions on Software Engineering, 2018.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_1_78_1","volume-title":"Azhar et al., \"Llama: Open and efficient foundation language models,\" arXiv preprint arXiv:2302.13971","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar et al., \"Llama: Open and efficient foundation language models,\" arXiv preprint arXiv:2302.13971, 2023."},{"key":"e_1_3_2_1_79_1","first-page":"42","article-title":"Study on the legal framework of text and data mining (tdm)","volume":"03","author":"Triaille J.-P.","year":"2014","unstructured":"J.-P. Triaille et al., \"Study on the legal framework of text and data mining (tdm),\" European Union Studies KM-03-13-42, 2014.","journal-title":"European Union Studies KM-"},{"key":"e_1_3_2_1_80_1","volume-title":"new york, 13-4829","author":"v. Google T. A. G.","year":"2015","unstructured":"T. A. G. v. Google, \"Us court of appeals, new york, 13-4829, 2015.\" 2015."},{"key":"e_1_3_2_1_81_1","first-page":"742","volume-title":"Tracing software build processes to uncover license compliance inconsistencies,\" in Proceedings of the 29th ACM\/IEEE international conference on Automated software engineering","author":"Van Der Burg S.","year":"2014","unstructured":"S. Van Der Burg, E. Dolstra, S. McIntosh, J. Davies, D. M. German, and A. Hemel, \"Tracing software build processes to uncover license compliance inconsistencies,\" in Proceedings of the 29th ACM\/IEEE international conference on Automated software engineering, 2014, pp. 731\u2013742."},{"key":"e_1_3_2_1_82_1","volume-title":"microsoft for allegedly infringing copyrighted work","author":"News VOA","year":"2023","unstructured":"VOA News, \"Ny times sues openai, microsoft for allegedly infringing copyrighted work,\" 2023. [Online]. Available: https:\/\/www.voanews.com\/a\/ny-times-sues-openai-microsoft-for-allegedly-infringing-copyrighted-work\/7414394.html"},{"key":"e_1_3_2_1_83_1","volume-title":"Hanfei","author":"Wen J.","year":"2023","unstructured":"J. Wen and W. He, \"Hanfei,\" 2023. [Online]. Available: https:\/\/github.com\/siat-nlp\/HanFei"},{"key":"e_1_3_2_1_84_1","unstructured":"G. Yadav \"Scaling evidence-based instructional design expertise through large language models \" arXiv preprint arXiv:2306.01006 2023."},{"key":"e_1_3_2_1_85_1","first-page":"13","volume-title":"Exploring the effectiveness of prompt engineering for legal reasoning tasks,\" in Findings of the Association for Computational Linguistics: ACL","author":"Yu F.","year":"2023","unstructured":"F. Yu, L. Quartey, and F. Schilder, \"Exploring the effectiveness of prompt engineering for legal reasoning tasks,\" in Findings of the Association for Computational Linguistics: ACL 2023, A. Rogers, J. Boyd-Graber, and N. Okazaki, Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp. 13 582\u201313 596. [Online]. Available: https:\/\/aclanthology.org\/2023.findings-acl.858"},{"key":"e_1_3_2_1_86_1","volume-title":"The cot collection: Improving zero-shot and few-shot learning of language models via chain-of-thought fine-tuning,\" arXiv preprint arXiv:2305.14045","author":"Zelikman E.","year":"2023","unstructured":"E. Zelikman et al., \"The cot collection: Improving zero-shot and few-shot learning of language models via chain-of-thought fine-tuning,\" arXiv preprint arXiv:2305.14045, 2023."},{"key":"e_1_3_2_1_87_1","volume-title":"Xia et al., \"Glm-130b: An open bilingual pre-trained model,\" arXiv preprint arXiv:2210.02414","author":"Zeng A.","year":"2022","unstructured":"A. Zeng, X. Liu, Z. Du, Z. Wang, H. Lai, M. Ding, Z. Yang, Y. Xu, W. Zheng, X. Xia et al., \"Glm-130b: An open bilingual pre-trained model,\" arXiv preprint arXiv:2210.02414, 2022."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00766-013-0181-8","article-title":"Gaiust: Supporting the extraction of rights and obligations for regulatory compliance","volume":"20","author":"Zeni N.","year":"2015","unstructured":"N. Zeni, N. Kiyavitskaya, L. Mich, J. R. Cordy, and J. Mylopoulos, \"Gaiust: Supporting the extraction of rights and obligations for regulatory compliance,\" Requirements Engineering, vol. 20, pp. 1\u201322, 2015.","journal-title":"Requirements Engineering"},{"key":"e_1_3_2_1_89_1","first-page":"3","volume-title":"IEEE","author":"Zhang H.","year":"2010","unstructured":"H. Zhang, B. Shi, and L. Zhang, \"Automatic checking of license compliance,\" in 2010 IEEE International Conference on Software Maintenance. IEEE, 2010, pp. 1\u20133."},{"key":"e_1_3_2_1_90_1","volume-title":"Adaptive budget allocation for parameter-efficient fine-tuning,\" arXiv preprint arXiv:2303.10512","author":"Zhang Q.","year":"2023","unstructured":"Q. Zhang, M. Chen, A. Bukharin, P. He, Y. Cheng, W. Chen, and T. Zhao, \"Adaptive budget allocation for parameter-efficient fine-tuning,\" arXiv preprint arXiv:2303.10512, 2023."},{"key":"e_1_3_2_1_91_1","volume-title":"Dong et al., \"A survey of large language models,\" arXiv preprint arXiv:2303.18223","author":"Zhao W. X.","year":"2023","unstructured":"W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong et al., \"A survey of large language models,\" arXiv preprint arXiv:2303.18223, 2023."}],"event":{"name":"FSE Companion '25: 33rd ACM International Conference on the Foundations of Software Engineering","location":"Clarion Hotel Trondheim Trondheim Norway","acronym":"FSE Companion '25","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696630.3728530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:14:39Z","timestamp":1753730079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696630.3728530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":91,"alternative-id":["10.1145\/3696630.3728530","10.1145\/3696630"],"URL":"https:\/\/doi.org\/10.1145\/3696630.3728530","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}