{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:03:17Z","timestamp":1777982597125,"version":"3.51.4"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005376","name":"Mid Sweden University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005376","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Requirements Eng"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Large Language Models (LLMs) have the potential to automate knowledge-intensive interactions in enterprise systems, yet their adoption is often limited. One reason is a lack of user trust. This study examines how trust can be\n                    <jats:italic>systematically engineered<\/jats:italic>\n                    into an LLM-driven, multi-agent chatbot that handles routine human-resources (HR) queries. We follow a two-cycle Design Science Research methodology. Cycle 1 triangulated a systematic literature review with a thematic analysis over semi-structured interviews of six employees at a global firm and a confirmatory workshop with five AI experts to elicit and validate\n                    <jats:italic>trust requirements<\/jats:italic>\n                    . Cycle II instantiated these requirements in a multi-agent LLM chatbot prototype artifact and evaluated whether the artifact satisfies them through controlled user sessions and expert walkthroughs, emphasizing perceived usefulness and\n                    <jats:italic>trust<\/jats:italic>\n                    captured in post-task interviews (\n                    <jats:inline-formula>\n                      <jats:tex-math>$$n = 11$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ) and operationalizing trust via alignment-oriented measures (faithfulness, answer relevancy, and adversarial robustness). The study yields a refined taxonomy of\n                    <jats:italic>external<\/jats:italic>\n                    (transparency, organizational safeguards, third-party security) and\n                    <jats:italic>internal<\/jats:italic>\n                    (model provenance, bias risk, reliability) trust factors, identifying\n                    <jats:italic>reliability<\/jats:italic>\n                    as the primary determinant of adoption. The implemented design achieved\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\ge 0.86$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    on trust-aligned metrics and was endorsed by 9\/11 participants as ready for field deployment. These findings demonstrate that trust can be proactively addressed through design and offer prescriptive guidelines for software engineers seeking to embed LLMs safely and responsibly in socio-technical contexts.\n                  <\/jats:p>","DOI":"10.1007\/s00766-026-00457-w","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:25:28Z","timestamp":1773656728000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Addressing trust requirements in the design of an open-source multi-agent LLM-based domain-specific chatbot"],"prefix":"10.1007","volume":"31","author":[{"given":"Jonatan","family":"Axetorn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Edholm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Dobslaw","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"Gren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"issue":"1","key":"457_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1057\/s41599-024-04044-8","volume":"11","author":"S Afroogh","year":"2024","unstructured":"Afroogh S, Akbari A, Malone E et al (2024) Trust in ai: progress, challenges, and future directions. Humanit Soc Sci Commun 11(1):1\u201330","journal-title":"Humanit Soc Sci Commun"},{"key":"457_CR2","unstructured":"Asai A, Wu Z, Wang Y, et\u00a0al (2024) Self-rag: learning to retrieve, generate, and critique through self-reflection. In: International conference on learning representations"},{"key":"457_CR3","doi-asserted-by":"publisher","unstructured":"Ayala O, Bechard P (2024) Reducing hallucination in structured outputs via retrieval-augmented generation. In: Proceedings of the 2024 conference of the north American chapter of the association for computational linguistics: human language technologies (Volume 6: Industry Track). Association for Computational Linguistics, pp 228\u2013238, https:\/\/doi.org\/10.18653\/v1\/2024.naacl-industry.19","DOI":"10.18653\/v1\/2024.naacl-industry.19"},{"key":"457_CR4","unstructured":"Ayyamperumal SG, Ge L (2024) Current state of LLM Risks and AI guardrails. arXiv:2406.12934"},{"key":"457_CR5","doi-asserted-by":"publisher","unstructured":"Baltes S, Speith T, Chiteri B, et\u00a0al (2025) On the need to rethink trust in ai assistants for software development: a critical review. https:\/\/doi.org\/10.48550\/arXiv.2504.12461, arXiv preprint, arXiv:2504.12461","DOI":"10.48550\/arXiv.2504.12461"},{"key":"457_CR6","doi-asserted-by":"crossref","unstructured":"Barone AM, Stagno E (2023) Chatbots. In: Artificial intelligence along the customer journey: a customer experience perspective. Springer, pp 37\u201354","DOI":"10.1007\/978-3-031-48792-7_3"},{"key":"457_CR7","doi-asserted-by":"publisher","unstructured":"Borg M, Bengtsson J, \u00d6sterling H, et\u00a0al (2022) Quality assurance of generative dialog models in an evolving conversational agent used for swedish language practice. In: Proceedings of the 1st international conference on ai engineering \u2013 software engineering for AI (CAIN \u201922). ACM, New York, NY, USA, pp 22\u201332, https:\/\/doi.org\/10.1145\/3522664.3528592","DOI":"10.1145\/3522664.3528592"},{"key":"457_CR8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","volume":"3","author":"V Braun","year":"2006","unstructured":"Braun V, Clarke V (2006) Using thematic analysis in psychology. Qual Res Psychol 3:77\u2013101. https:\/\/doi.org\/10.1191\/1478088706qp063oa","journal-title":"Qual Res Psychol"},{"key":"457_CR9","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N 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":"457_CR10","unstructured":"Chang CY, Jiang Z, Rakesh V, et\u00a0al (2024) Main-rag: multi-agent filtering retrieval-augmented generation. arXiv preprint arXiv:2501.00332"},{"key":"457_CR11","unstructured":"Confident AI (2025a) DeepEval. https:\/\/www.deepeval.com\/docs\/metrics-introduction, Accessed 20 April 2025"},{"key":"457_CR12","unstructured":"Confident AI (2025b) Llm evaluation metrics - deepeval. https:\/\/www.deepeval.com\/docs\/metrics-llm-evals, Accessed 03 Aug 2025"},{"key":"457_CR13","unstructured":"Devlin J, Chang MW, Lee K, et\u00a0al (2019) 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, vol 1 (Long and Short Papers), pp 4171\u20134186"},{"key":"457_CR14","unstructured":"Dobslaw F, Feldt R, Yoon J, et\u00a0al (2025) Challenges in testing large language model based software: a faceted taxonomy. arXiv preprint arXiv:2503.00481"},{"key":"457_CR15","unstructured":"Dong Y, Mu R, Zhang Y, et\u00a0al (2024) Safeguarding large language models: a survey. arXiv preprint arXiv:2406.02622"},{"key":"457_CR16","unstructured":"Dorfner FJ, J\u00fcrgensen L, Donle L, et\u00a0al (2024) Is open-source there yet? A comparative study on commercial and open-source LLMs in their ability to label chest X-ray reports. arXiv preprint arXiv:2402.12298"},{"key":"457_CR17","unstructured":"Douze M, Guzhva A, Deng C, et\u00a0al (2025) The Faiss library. arXiv:2401.08281"},{"key":"457_CR18","doi-asserted-by":"crossref","unstructured":"Es S, James J, Anke LE, et\u00a0al (2024) Ragas: automated evaluation of retrieval augmented generation. In: Proceedings of the 18th conference of the European chapter of the association for computational linguistics: system demonstrations, pp 150\u2013158","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"457_CR19","unstructured":"FlagEmbedding (2024) BAAI\/bge-small-en-v1.5. https:\/\/huggingface.co\/BAAI\/bge-small-en-v1.5, Accessed 09 May 2025"},{"key":"457_CR20","doi-asserted-by":"crossref","unstructured":"Gao C, Chen X, Zhang G (2025) Sva-icl: improving llm-based software vulnerability assessment via in-context learning and information fusion. Inf Softw Technol pp 107803","DOI":"10.1016\/j.infsof.2025.107803"},{"key":"457_CR21","unstructured":"Gao Y, Xiong Y, Gao X, et\u00a0al (2024) Retrieval-Augmented generation for large language models: a survey. arXiv:2312.10997"},{"key":"457_CR22","unstructured":"Han S, Zhang Q, Yao Y, et\u00a0al (2024) Llm multi-agent systems: challenges and open problems. arXiv preprint arXiv:2402.03578"},{"issue":"3","key":"457_CR23","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1177\/0018720814547570","volume":"57","author":"KA Hoff","year":"2015","unstructured":"Hoff KA, Bashir M (2015) Trust in automation: integrating empirical evidence on factors that influence trust. Hum Factors 57(3):407\u2013434. https:\/\/doi.org\/10.1177\/0018720814547570","journal-title":"Hum Factors"},{"key":"457_CR24","doi-asserted-by":"publisher","unstructured":"Huang Y, Sun L, Wang H, et\u00a0al (2024a) Position: TRUSTLLM: Trustworthiness in large language models. In: Proceedings of machine learning research (ICML 2024), pp 20166\u201320270, https:\/\/proceedings.mlr.press\/v235\/huang24x.html, also available as arXiv:2401.05561, https:\/\/doi.org\/10.48550\/arXiv.2401.05561","DOI":"10.48550\/arXiv.2401.05561"},{"key":"457_CR25","unstructured":"Huang Y, Sun L, Wang H, et\u00a0al (2024b) Trustllm: trustworthiness in large language models. arXiv preprint arXiv:2401.05561"},{"key":"457_CR26","first-page":"223","volume":"2023","author":"T Jayakumar","year":"2023","unstructured":"Jayakumar T, Farooqui F, Farooqui L (2023) Large language models are legal but they are not: making the case for a powerful legalllm. Proc Nat Legal Lang Process Workshop 2023:223\u2013229","journal-title":"Proc Nat Legal Lang Process Workshop"},{"issue":"12","key":"457_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji Z, Lee N, Frieske R et al (2023) Survey of hallucination in natural language generation. ACM Comput Surv 55(12):1\u201338","journal-title":"ACM Comput Surv"},{"key":"457_CR28","doi-asserted-by":"crossref","unstructured":"Kaas MH, Porter Z, Lim E, et\u00a0al (2023) Ethics in conversation: building an ethics assurance case for autonomous ai-enabled voice agents in healthcare. In: Proceedings of the first international symposium on trustworthy autonomous systems, pp 1\u201313","DOI":"10.1145\/3597512.3599713"},{"issue":"3","key":"457_CR29","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1002\/asi.20722","volume":"59","author":"K Kelton","year":"2008","unstructured":"Kelton K, Fleischmann KR, Wallace WA (2008) Trust in digital information. J Am Soc Inform Sci Technol 59(3):363\u2013374","journal-title":"J Am Soc Inform Sci Technol"},{"key":"457_CR30","doi-asserted-by":"crossref","unstructured":"Knauss E (2021) Constructive master\u2019s thesis work in industry: guidelines for applying design science research. In: 2021 IEEE\/ACM 43rd international conference on software engineering: software engineering education and training (ICSE-SEET), IEEE, pp 110\u2013121","DOI":"10.1109\/ICSE-SEET52601.2021.00021"},{"issue":"1","key":"457_CR31","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1518\/hfes.46.1.50_30392","volume":"46","author":"JD Lee","year":"2004","unstructured":"Lee JD, See KA (2004) Trust in automation: designing for appropriate reliance. Hum Factors 46(1):50\u201380. https:\/\/doi.org\/10.1518\/hfes.46.1.50_30392","journal-title":"Hum Factors"},{"key":"457_CR32","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A et al (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst 33:9459\u20139474","journal-title":"Adv Neural Inf Process Syst"},{"key":"457_CR33","unstructured":"Li W, Wang X, Li W, et\u00a0al (2025) A survey of automatic prompt engineering: an optimization perspective. arXiv:2502.11560"},{"issue":"1","key":"457_CR34","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44336-024-00009-2","volume":"1","author":"X Li","year":"2024","unstructured":"Li X, Wang S, Zeng S et al (2024) A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1(1):9","journal-title":"Vicinagearth"},{"key":"457_CR35","doi-asserted-by":"crossref","unstructured":"Liang T, He Z, Jiao W, et\u00a0al (2024) Encouraging divergent thinking in large language models through multi-agent debate. In: Proceedings of the 2024 conference on empirical methods in natural language processing, pp 17889\u201317904","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"457_CR36","unstructured":"Liu Y, Yao Y, Ton JF, et\u00a0al (2024) Trustworthy LLMs: a survey and guideline for evaluating large language models\u2019 alignment. arXiv:2308.05374"},{"key":"457_CR37","unstructured":"Manchanda J, Boettcher L, Westphalen M, et\u00a0al (2024) The open source advantage in large language models (LLMs). arXiv preprint arXiv:2412.12004"},{"issue":"3","key":"457_CR38","doi-asserted-by":"publisher","first-page":"709","DOI":"10.2307\/258792","volume":"20","author":"RC Mayer","year":"1995","unstructured":"Mayer RC, Davis JH, Schoorman FD (1995) An integrative model of organizational trust. Acad Manag Rev 20(3):709\u2013734","journal-title":"Acad Manag Rev"},{"key":"457_CR39","unstructured":"McNamara C (2017) General guidelines for conducting research interviews. http:\/\/managementhelp.org\/businessresearch\/interviews.htm, Retrieved 6 March 2025"},{"issue":"3","key":"457_CR40","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s10664-025-10625-1","volume":"30","author":"SK Pandey","year":"2025","unstructured":"Pandey SK, Chand S, Horkoff J et al (2025) Design pattern recognition: a study of large language models. Empir Softw Eng 30(3):69","journal-title":"Empir Softw Eng"},{"key":"457_CR41","volume-title":"Qualitative research and evaluation methods: integrating theory and practice","author":"MQ Patton","year":"2014","unstructured":"Patton MQ (2014) Qualitative research and evaluation methods: integrating theory and practice, 4th edn. SAGE Publications, Thousand Oaks, CA","edition":"4"},{"issue":"1","key":"457_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1037\/0003-066X.35.1.1","volume":"35","author":"JB Rotter","year":"1980","unstructured":"Rotter JB (1980) Interpersonal trust, trustworthiness, and gullibility. Am Psychol 35(1):1","journal-title":"Am Psychol"},{"key":"457_CR43","unstructured":"Schwartz S, Yaeli A, Shlomov S (2023) Enhancing trust in llm-based ai automation agents: new considerations and future challenges. arXiv:2308.05391"},{"key":"457_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2024.107610","volume":"178","author":"A Sergeyuk","year":"2025","unstructured":"Sergeyuk A, Golubev Y, Bryksin T et al (2025) Using ai-based coding assistants in practice: state of affairs, perceptions, and ways forward. Inf Softw Technol 178:107610","journal-title":"Inf Softw Technol"},{"key":"457_CR45","doi-asserted-by":"crossref","unstructured":"Shen X, Chen Z, Backes M, et\u00a0al (2024) \u201cDo Anything Now\u201d: characterizing and evaluating in-the-wild jailbreak prompts on large language models. In: Proceedings of the 2024 on ACM SIGSAC conference on computer and communications security, pp 1671\u20131685","DOI":"10.1145\/3658644.3670388"},{"key":"457_CR46","doi-asserted-by":"crossref","unstructured":"Shettigar R (2024) AI in human resource: an empirical research on the impact, adoption, and employee perspectives. In: 2024 International conference on trends in quantum computing and emerging business technologies, pp 1\u20134","DOI":"10.1109\/TQCEBT59414.2024.10545262"},{"issue":"3","key":"457_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3241743","volume":"27","author":"KJ Stol","year":"2018","unstructured":"Stol KJ, Fitzgerald B (2018) The abc of software engineering research. ACM Trans Softw Eng Methodol (TOSEM) 27(3):1\u201351","journal-title":"ACM Trans Softw Eng Methodol (TOSEM)"},{"key":"457_CR48","unstructured":"Tran KT, Dao D, Nguyen MD, et\u00a0al (2025) Multi-agent collaboration mechanisms: a survey of llms. arXiv preprint arXiv:2501.06322"},{"issue":"6","key":"457_CR49","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang L, Ma C, Feng X et al (2024) A survey on large language model based autonomous agents. Front Comp Sci 18(6):186345","journal-title":"Front Comp Sci"},{"key":"457_CR50","doi-asserted-by":"crossref","unstructured":"Wieringa R (2009) Design science as nested problem solving. In: Proceedings of the 4th international conference on design science research in information systems and technology, pp 1\u201312","DOI":"10.1145\/1555619.1555630"},{"issue":"2","key":"457_CR51","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1017\/S0269888900008122","volume":"10","author":"M Wooldridge","year":"1995","unstructured":"Wooldridge M, Jennings NR (1995) Intelligent agents: theory and practice. The Knowl Eng Rev 10(2):115\u2013152","journal-title":"The Knowl Eng Rev"},{"issue":"2","key":"457_CR52","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0","volume":"68","author":"Z Xi","year":"2025","unstructured":"Xi Z, Chen W, Guo X et al (2025) The rise and potential of large language model based agents: a survey. Sci China Inf Sci 68(2):121101","journal-title":"Sci China Inf Sci"},{"key":"457_CR53","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng L, Chiang WL, Sheng Y et al (2023) Judging llm-as-a-judge with mt-bench and chatbot arena. Adv Neural Inf Process Syst 36:46595\u201346623","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Requirements Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00766-026-00457-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00766-026-00457-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00766-026-00457-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:25:48Z","timestamp":1773656748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00766-026-00457-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["457"],"URL":"https:\/\/doi.org\/10.1007\/s00766-026-00457-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7494256\/v1","asserted-by":"object"}]},"ISSN":["0947-3602","1432-010X"],"issn-type":[{"value":"0947-3602","type":"print"},{"value":"1432-010X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"30 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"3"}}