{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:40:41Z","timestamp":1792514441748,"version":"4.5.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031758713","type":"print"},{"value":"9783031758720","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-75872-0_16","type":"book-chapter","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T01:02:23Z","timestamp":1729904543000},"page":"295-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Establishing Traceability Between Natural Language Requirements and\u00a0Software Artifacts by\u00a0Combining RAG and\u00a0LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0710-8052","authenticated-orcid":false,"given":"Syed Juned","family":"Ali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Naganathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8259-2297","authenticated-orcid":false,"given":"Dominik","family":"Bork","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"16_CR1","unstructured":"Center of excellence for software & systems traceability (COEST) (2024). http:\/\/sarec.nd.edu\/coest\/datasets.html. Accessed 3 June 2024"},{"key":"16_CR2","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"16_CR3","unstructured":"Booch, G., Rumbaugh, J.E., Jacobson, I.: The Unified Modeling Language User Guide - Covers UML 2.0. 2nd edn. Addison Wesley Object Technology Series. Addison-Wesley (2005)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: M3-embedding: multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 2318\u20132335 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Wang, D., Shi, L., Wang, Q.: A self-enhanced automatic traceability link recovery via structure knowledge mining for small-scale labeled data. In: 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 904\u2013913. IEEE (2021)","DOI":"10.1109\/COMPSAC51774.2021.00123"},{"key":"16_CR6","unstructured":"De\u00a0La\u00a0Vara, J.L., Wnuk, K., Berntsson-Svensson, R., S\u00e1nchez, J., Regnell, B.: An empirical study on the importance of quality requirements in industry. In: SEKE, pp. 438\u2013443 (2011)"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/V1\/N19-1423","DOI":"10.18653\/V1\/N19-1423"},{"issue":"11","key":"16_CR8","first-page":"42","volume":"6","author":"K Divya","year":"2014","unstructured":"Divya, K., Subha, R., Palaniswami, S.: Similar words identification using Naive and TF-IDF method. Int. J. Inf. Technol. Comput. Sci. (IJITCS) 6(11), 42 (2014)","journal-title":"Int. J. Inf. Technol. Comput. Sci. (IJITCS)"},{"key":"16_CR9","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-319-49421-0_2","volume-title":"Software Quality. Complexity and Challenges of Software Engineering in Emerging Technologies","author":"M Eyl","year":"2017","unstructured":"Eyl, M., Reichmann, C., M\u00fcller-Glaser, K.: Traceability in a fine grained software configuration management system. In: Winkler, D., Biffl, S., Bergsmann, J. (eds.) SWQD 2017. LNBIP, vol. 269, pp. 15\u201329. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-49421-0_2"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Ezzini, S., Abualhaija, S., Arora, C., Sabetzadeh, M.: Automated handling of anaphoric ambiguity in requirements: a multi-solution study. In: Proceedings of the 44th International Conference on Software Engineering, pp. 187\u2013199 (2022)","DOI":"10.1145\/3510003.3510157"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Gotel, O., et al.: The grand challenge of traceability (v1. 0). In: Software Systems Traceability, pp. 343\u2013409 (2012)","DOI":"10.1007\/978-1-4471-2239-5_16"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Guerrouj, L., Bourque, D., Rigby, P.C.: Leveraging informal documentation to summarize classes and methods in context. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering, vol.\u00a02, pp. 639\u2013642. IEEE (2015)","DOI":"10.1109\/ICSE.2015.212"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Hadi, M.U., et\u00a0al.: A survey on large language models: applications, challenges, limitations, and practical usage. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.23589741.v1"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Hey, T., Chen, F., Weigelt, S., Tichy, W.F.: Improving traceability link recovery using fine-grained requirements-to-code relations. In: 2021 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 12\u201322. IEEE (2021)","DOI":"10.1109\/ICSME52107.2021.00008"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Hou, X., et al.: Large language models for software engineering: a systematic literature review. CoRR abs\/2308.10620 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2308.10620","DOI":"10.48550\/ARXIV.2308.10620"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Liu, Z., Chen, X., Luo, X.: Automatic matching release notes and source code by generating summary for software change. In: 2016 6th International Conference on Digital Home (ICDH), pp. 104\u2013109. IEEE (2016)","DOI":"10.1109\/ICDH.2016.031"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Iyer, S., Konstas, I., Cheung, A., Zettlemoyer, L.: Summarizing source code using a neural attention model. In: 54th Annual Meeting of the Association for Computational Linguistics 2016, pp. 2073\u20132083. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1195"},{"key":"16_CR18","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: Spanbert: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguist. 8, 64\u201377 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274","volume":"103","author":"E Kasneci","year":"2023","unstructured":"Kasneci, E., et al.: Chatgpt for good? On opportunities and challenges of large language models for education. Learn. Individ. Differ. 103, 102274 (2023)","journal-title":"Learn. Individ. Differ."},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Khlif, W., Kchaou, D., Bouassida, N.: A complete traceability methodology between UML diagrams and source code based on enriched use case textual description. Informatica 46(1) (2022)","DOI":"10.31449\/inf.v46i1.3306"},{"issue":"6","key":"16_CR21","doi-asserted-by":"publisher","first-page":"540","DOI":"10.4097\/kjae.2015.68.6.540","volume":"68","author":"TK Kim","year":"2015","unstructured":"Kim, T.K.: T test as a parametric statistic. Korean J. Anesthesiol. 68(6), 540 (2015)","journal-title":"Korean J. Anesthesiol."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Liang, Y., Zhu, K.: Automatic generation of text descriptive comments for code blocks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11963"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, Y., Zeng, Q., Jiang, M., Cleland-Huang, J.: Traceability transformed: generating more accurate links with pre-trained BERT models. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE), pp. 324\u2013335. IEEE (2021)","DOI":"10.1109\/ICSE43902.2021.00040"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zou, Y., Zhao, J., Xie, B.: Improving software text retrieval using conceptual knowledge in source code. In: 2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 123\u2013134. IEEE (2017)","DOI":"10.1109\/ASE.2017.8115625"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Lohar, S., Amornborvornwong, S., Zisman, A., Cleland-Huang, J.: Improving trace accuracy through data-driven configuration and composition of tracing features. In: Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering, pp. 378\u2013388 (2013)","DOI":"10.1145\/2491411.2491432"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Mills, C., Escobar-Avila, J., Haiduc, S.: Automatic traceability maintenance via machine learning classification. In: 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 369\u2013380. IEEE (2018)","DOI":"10.1109\/ICSME.2018.00045"},{"key":"16_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2023.102994","volume":"230","author":"A Moharil","year":"2023","unstructured":"Moharil, A., Sharma, A.: Tabasco: a transformer based contextualization toolkit. Sci. Comput. Program. 230, 102994 (2023)","journal-title":"Sci. Comput. Program."},{"key":"16_CR28","unstructured":"Moore, R.C., Lewis, W.: Intelligent selection of language model training data. In: Proceedings of the ACL 2010 Conference Short Papers, pp. 220\u2013224 (2010)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Moran, K., et al.: Improving the effectiveness of traceability link recovery using hierarchical Bayesian networks. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering, pp. 873\u2013885 (2020)","DOI":"10.1145\/3377811.3380418"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Nejati, S., Sabetzadeh, M., Arora, C., Briand, L.C., Mandoux, F.: Automated change impact analysis between sysml models of requirements and design. In: Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 242\u2013253 (2016)","DOI":"10.1145\/2950290.2950293"},{"key":"16_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111616","volume":"198","author":"Z Pauzi","year":"2023","unstructured":"Pauzi, Z., Capiluppi, A.: Applications of natural language processing in software traceability: a systematic mapping study. J. Syst. Softw. 198, 111616 (2023)","journal-title":"J. Syst. Softw."},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Robertson, S., Zaragoza, H., et\u00a0al.: The probabilistic relevance framework: BM25 and beyond. Found. Trends\u00aeInf. Retrieval 3(4), 333\u2013389 (2009)","DOI":"10.1561\/1500000019"},{"key":"16_CR33","unstructured":"Sridhara, G., Mazumdar, S., et\u00a0al.: Chatgpt: a study on its utility for ubiquitous software engineering tasks. arXiv preprint arXiv:2305.16837 (2023)"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Tian, Q., Cao, Q., Sun, Q.: Adapting word embeddings to traceability recovery. In: 2018 International Conference on Information Systems and Computer Aided Education (ICISCAE), pp. 255\u2013261. IEEE (2018)","DOI":"10.1109\/ICISCAE.2018.8666883"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Wan, Y., et al.: Improving automatic source code summarization via deep reinforcement learning. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering, pp. 397\u2013407 (2018)","DOI":"10.1145\/3238147.3238206"},{"issue":"3","key":"16_CR36","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1108\/00330330610681295","volume":"40","author":"P Willett","year":"2006","unstructured":"Willett, P.: The porter stemming algorithm: then and now. Program 40(3), 219\u2013223 (2006)","journal-title":"Program"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Wohlin, C., Runeson, P., H\u00f6st, M., Ohlsson, M.C., Regnell, B., Wessl\u00e9n, A.: Experimentation in Software Engineering. Springer, Heidelberg (2012)","DOI":"10.1007\/978-3-642-29044-2"},{"issue":"4","key":"16_CR38","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1049\/sfw2.12082","volume":"17","author":"C Xu","year":"2023","unstructured":"Xu, C., Li, Y., Wang, B., Dong, S.: A systematic mapping study on machine learning methodologies for requirements management. IET Software 17(4), 405\u2013423 (2023)","journal-title":"IET Software"},{"key":"16_CR39","doi-asserted-by":"publisher","unstructured":"Yazawa, Y., Ogata, S., Okano, K., Kaiya, H., Washizaki, H.: Traceability link mining - focusing on usability. In: 41st IEEE Annual Computer Software and Applications Conference, COMPSAC 2017, vol. 2, pp. 286\u2013287. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/COMPSAC.2017.254","DOI":"10.1109\/COMPSAC.2017.254"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Yin, P., Neubig, G.: A syntactic neural model for general-purpose code generation. arXiv preprint arXiv:1704.01696 (2017)","DOI":"10.18653\/v1\/P17-1041"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Zan, D., et al.: Large language models meet NL2Code: a survey. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7443\u20137464 (2023)","DOI":"10.18653\/v1\/2023.acl-long.411"}],"container-title":["Lecture Notes in Computer Science","Conceptual Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-75872-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T01:05:00Z","timestamp":1729904700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-75872-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"ISBN":["9783031758713","9783031758720"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-75872-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"21 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ER","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Conceptual Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pittsburg, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"er2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/resources.sei.cmu.edu\/news-events\/events\/er2024\/cfp.cfm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}