{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:22:21Z","timestamp":1758273741679,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031432392"},{"type":"electronic","value":"9783031432408"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43240-8_16","type":"book-chapter","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T02:01:58Z","timestamp":1695002518000},"page":"247-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Applying Pairwise Combinatorial Testing to\u00a0Large Language Model Testing"],"prefix":"10.1007","author":[{"given":"Bernhard","family":"Garn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ludwig","family":"Kampel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Leithner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berina","family":"Celic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ceren","family":"\u00c7ulha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irene","family":"Hiess","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klaus","family":"Kieseberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marlene","family":"Koelbing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik-Philip","family":"Schreiber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Wech","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jovan","family":"Zivanovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris E.","family":"Simos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,19]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 632\u2013642 (2015)","DOI":"10.18653\/v1\/D15-1075"},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s11219-020-09544-9","volume":"30","author":"J Bo\u017ei\u0107","year":"2022","unstructured":"Bo\u017ei\u0107, J.: Ontology-based metamorphic testing for chatbots. Softw. Qual. J. 30(1), 227\u2013251 (2022)","journal-title":"Softw. Qual. J."},{"key":"16_CR3","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., et al.: Language Models are Few-Shot Learners. In: Advance in Neural Information Proceedings Systems, vol. 33, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Clark, C., Lee, K., Chang, M.W., Kwiatkowski, T., Collins, M., Toutanova, K.: BoolQ: exploring the surprising difficulty of natural yes\/no questions. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol 1. pp. 2924\u20132936 (2019)","DOI":"10.18653\/v1\/N19-1300"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Gardner, M., Artzi, Y., Basmov, V., Berant, J., Bogin, B., Chen, S., et al.: Evaluating models\u2019 local decision boundaries via contrast sets. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1307\u20131323 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Grindal, M., Offutt, J.: Input parameter modeling for combination strategies. In: Proceedings of the 25th Conference on IASTED International Multi-Conference: Software Engineering, pp. 255\u2013260. SE 2007, ACTA Press, Anaheim, CA, USA (2007)","DOI":"10.1109\/ASWEC.2007.27"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Guichard, J., Ruane, E., Smith, R., Bean, D., Ventresque, A.: Assessing the robustness of conversational agents using paraphrases. In: 2019 IEEE International Conference On Artificial Intelligence Testing (AITest), pp. 55\u201362 (2019)","DOI":"10.1109\/AITest.2019.000-7"},{"key":"16_CR8","unstructured":"Jang, M., Lukasiewicz, T.: Consistency analysis of chatgpt. arXiv preprint arXiv:2303.06273 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.06273"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Khashabi, D., Khot, T., Sabharwal, A.: More bang for your buck: natural perturbation for robust question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 163\u2013170 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.12"},{"key":"16_CR10","unstructured":"Kuhn, D., Kacker, R., Lei, Y.: Introduction to Combinatorial Testing. Chapman & Hall\/CRC Innovations in Software Engineering and Software Development Series, Taylor & Francis Group, CRC Press, Boca Raton, Florida (2013)"},{"issue":"2","key":"16_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1883612.1883618","volume":"43","author":"C Nie","year":"2011","unstructured":"Nie, C., Leung, H.: A survey of combinatorial testing. ACM Comput. Surv. 43(2), 1\u201329 (2011). https:\/\/doi.org\/10.1145\/1883612.1883618","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"16_CR12","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR13","unstructured":"Ruane, E., Faure, T., Smith, R., Bean, D., Carson-Berndsen, J., Ventresque, A.: BoTest: a framework to test the quality of conversational agents using divergent input examples. In: Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion. IUI 20118 Companion, ACM, New York, NY, USA (2018)"},{"key":"16_CR14","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3645\u20133650"},{"key":"16_CR15","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., et al.: Llama: open and efficient foundation language models. Preprint arXiv:2302.13971 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.13971"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Wagner, M., Kleine, K., Simos, D.E., Kuhn, R., Kacker, R.: CAGEN: a fast combinatorial test generation tool with support for constraints and higher-index arrays. In: 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pp. 191\u2013200 (2020)","DOI":"10.1109\/ICSTW50294.2020.00041"},{"key":"16_CR17","unstructured":"Wotawa, F.: On the use of available testing methods for verification & validation of AI-based software and systems. In: CEUR Workshop Proceedings 2808 (2021)"}],"container-title":["Lecture Notes in Computer Science","Testing Software and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43240-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T07:06:15Z","timestamp":1730099175000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43240-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031432392","9783031432408"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43240-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICTSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Testing Software and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergamo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pts2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ictss-2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"56","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1 Journal first","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}