{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:03:58Z","timestamp":1743120238855,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031735028"},{"type":"electronic","value":"9783031735035"}],"license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"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\/978-3-031-73503-5_25","type":"book-chapter","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T04:00:59Z","timestamp":1731643259000},"page":"305-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing the\u00a0Trustworthiness of\u00a0Large Language Models on\u00a0Domain-Specific Questions"],"prefix":"10.1007","author":[{"given":"Sandra","family":"Mitrovi\u0107","sequence":"first","affiliation":[]},{"given":"Matteo","family":"Mazzola","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Larcher","sequence":"additional","affiliation":[]},{"given":"J\u00e9r\u00f4me","family":"Guzzi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"key":"25_CR1","unstructured":"Damodaran, P.: Parrot: paraphrase generation for NLU. (2021)"},{"key":"25_CR2","unstructured":"Es, S., James, J., Espinosa\u00a0Anke, L., Schockaert, S.: 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 (2024)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Jang, M., Lukasiewicz, T.: Consistency analysis of ChatGPT. arXiv preprint arXiv:2303.06273 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.991"},{"key":"25_CR4","doi-asserted-by":"publisher","unstructured":"Johnson, D., et\u00a0al.: Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model. Res Sq [Preprint]. 28 Feb 2023. rs.3.rs-2566942. https:\/\/doi.org\/10.21203\/rs.3.rs-2566942\/v1. PMID: 36909565; PMCID: PMC10002821","DOI":"10.21203\/rs.3.rs-2566942\/v1"},{"key":"25_CR5","doi-asserted-by":"publisher","first-page":"57","DOI":"10.7494\/csci.2019.20.1.3023","volume":"20","author":"M Jungiewicz","year":"2019","unstructured":"Jungiewicz, M., Smywi\u0144ski-Pohl, A.: Towards textual data augmentation for neural networks: synonyms and maximum loss. Comput. Sci. 20, 57\u201383 (2019)","journal-title":"Comput. Sci."},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Kale, M., Rastogi, A.: Text-to-text pre-training for data-to-text tasks. In: Proceedings of the 13th International Conference on Natural Language Generation, pp. 97\u2013102. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.inlg-1.14"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Khatun, A., Brown, D.G.: Reliability check: an analysis of GPT-3\u2019s response to sensitive topics and prompt wording. arXiv preprint arXiv:2306.06199 (2023)","DOI":"10.18653\/v1\/2023.trustnlp-1.8"},{"key":"25_CR8","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9459\u20139474 (2020)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Li, J., et\u00a0al.: Are you asking GPT-4 medical questions properly?-prompt engineering in consistency and reliability with evidence-based guidelines for ChatGPT-4: A pilot study. npj Digit. Med. 7, 41 (2023)","DOI":"10.21203\/rs.3.rs-3336823\/v1"},{"key":"25_CR10","unstructured":"Liu, Y., et\u00a0al.: Trustworthy LLMs: a survey and guideline for evaluating large language models\u2019 alignment. arXiv preprint arXiv:2308.05374 (2023)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. arXiv preprint arXiv:1511.06709 (2015)","DOI":"10.18653\/v1\/P16-1009"},{"key":"25_CR12","unstructured":"Shen, X., Chen, Z., Backes, M., Zhang, Y.: In ChatGPT we trust? measuring and characterizing the reliability of ChatGPT. arXiv preprint arXiv:2304.08979 (2023)"},{"key":"25_CR13","unstructured":"Si, C., et\u00a0al.: Prompting GPT-3 to be reliable. arXiv preprint arXiv:2210.09150 (2022)"},{"issue":"7","key":"25_CR14","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1080\/10447318.2022.2101698","volume":"39","author":"A Silva","year":"2023","unstructured":"Silva, A., Schrum, M., Hedlund-Botti, E., Gopalan, N., Gombolay, M.: Explainable artificial intelligence: evaluating the objective and subjective impacts of XAI on human-agent interaction. Int. J. Hum. Comput. Interact. 39(7), 1390\u20131404 (2023)","journal-title":"Int. J. Hum. Comput. Interact."},{"issue":"1","key":"25_CR15","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1111\/iej.13985","volume":"57","author":"A Su\u00e1rez","year":"2024","unstructured":"Su\u00e1rez, A., et al.: Unveiling the ChatGPT phenomenon: evaluating the consistency and accuracy of endodontic question answers. Int. Endod. J. 57(1), 108\u2013113 (2024)","journal-title":"Int. Endod. J."},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W.Y., Yang, D.: That\u2019s so annoying!!!: a lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using# petpeeve tweets. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2557\u20132563 (2015)","DOI":"10.18653\/v1\/D15-1306"},{"key":"25_CR17","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: pre-training with extracted gap-sentences for abstractive summarization. arXiv:1912.08777 (2019)"},{"key":"25_CR18","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"25_CR19","unstructured":"Zhong, L., Wang, Z.: A study on robustness and reliability of large language model code generation. arXiv preprint arXiv:2308.10335 (2023)"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73503-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:17:10Z","timestamp":1731647830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73503-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"ISBN":["9783031735028","9783031735035"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73503-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,16]]},"assertion":[{"value":"16 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Viana do Castelo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"3 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2024.pt","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}