{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T11:02:44Z","timestamp":1755601364777,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887130","type":"print"},{"value":"9783031887147","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-88714-7_10","type":"book-chapter","created":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:42:18Z","timestamp":1743853338000},"page":"128-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Ranking Generated Answers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7701-3294","authenticated-orcid":false,"given":"Sebastian","family":"Heineking","sequence":"first","affiliation":[]},{"given":"Jonas","family":"Probst","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2364-598X","authenticated-orcid":false,"given":"Daniel","family":"Steinbach","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2451-0665","authenticated-orcid":false,"given":"Martin","family":"Potthast","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-7157","authenticated-orcid":false,"given":"Harrisen","family":"Scells","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Arabzadeh, N., Clarke, C.L.A.: A Comparison of Methods for Evaluating Generative IR. CoRR (2024). https:\/\/doi.org\/10.48550\/arxiv.2404.04044","DOI":"10.48550\/arxiv.2404.04044"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Berberette, E., Hutchins, J., Sadovnik, A.: Redefining \u201cHallucination\u201d in LLMs: towards a psychology-unformed framework for mitigating misinformation. CoRR (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.01769","DOI":"10.48550\/arXiv.2402.01769"},{"key":"10_CR3","doi-asserted-by":"publisher","unstructured":"Duh, K.: Ranking vs. regression in machine translation evaluation. In: Proceedings of the Third Workshop on Statistical Machine Translation. StatMT \u201908, USA, pp. 191\u2013194. Association for Computational Linguistics (2008). ISBN 9781932432091, https:\/\/doi.org\/10.5555\/1626394.1626425","DOI":"10.5555\/1626394.1626425"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Fan, A., Jernite, Y., Perez, E., Grangier, D., Weston, J., Auli, M.: ELI5: Long form question answering. In: ACL, pp. 3558\u20133567 (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1346","DOI":"10.18653\/v1\/P19-1346"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Farzi, N., Dietz, L.: Pencils down! Automatic rubric-based evaluation of retrieve\/generate systems. In: Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval. ICTIR \u201924, New York, NY, USA, pp. 175\u2013184. Association for Computing Machinery (2024), ISBN 9798400706813, https:\/\/doi.org\/10.1145\/3664190.3672511","DOI":"10.1145\/3664190.3672511"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Gienapp, L., et al.: Evaluating generative ad hoc information retrieval. In: Yang, G., Wang, H., Han, S., Hauff, C., Zuccon, G., Zhang, Y. (eds.) 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024), pp. 1916\u20131929. ACM (2024). ISBN 9798400704314, https:\/\/doi.org\/10.1145\/3626772.3657849","DOI":"10.1145\/3626772.3657849"},{"key":"10_CR7","unstructured":"Goeuriot, L., et al.: Consumer Health Search at CLEF eHealth 2021. In: (CEUR-WS.org), C.W.P. (ed.) CLEF 2021 Working Notes, CEUR Workshop Proceedings Vol. 2936., vol. 2936, Guglielmo Faggioli and Nicola Ferro and Alexis Joly and Maria Maistro and Florina Piroi, Bucharest, Romania (2021). https:\/\/hal.science\/hal-04109627"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Guzm\u00e1n, F., Joty, S., M\u00e0rquez, L., Nakov, P.: Pairwise neural machine translation evaluation. In: Zong, C., Strube, M. (eds.) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China, vol.\u00a01, pp. 805\u2013814. Association for Computational Linguistics (2015). https:\/\/doi.org\/10.3115\/v1\/P15-1078","DOI":"10.3115\/v1\/P15-1078"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201920, New York, NY, USA, pp. 39\u201348. Association for Computing Machinery (2020). ISBN 9781450380164, https:\/\/doi.org\/10.1145\/3397271.3401075","DOI":"10.1145\/3397271.3401075"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"Koopman, B., Zuccon, G.: Dr ChatGPT tell me what i want to hear: how different prompts impact health answer correctness. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, pp. 15012\u201315022. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.928","DOI":"10.18653\/v1\/2023.emnlp-main.928"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Krishna, K., Roy, A., Iyyer, M.: Hurdles to progress in long-form question answering. In: Toutanova, K., et al. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4940\u20134957. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.393","DOI":"10.18653\/v1\/2021.naacl-main.393"},{"key":"10_CR12","unstructured":"Li, M., Jiang, A., Wang, M.: Listwise approach to learning to rank for automatic evaluation of machine translation. In: Way, A., Sima\u2019an, K., Forcada, M.L. (eds.) Proceedings of Machine Translation Summit XIV: Papers, Nice, France (2013)"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Macdonald, C., Tonellotto, N.: Declarative experimentation in information retrieval using PyTerrier. In: Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval. ICTIR \u201920, New York, NY, USA, pp. 161\u2013168. Association for Computing Machinery (2020), ISBN 9781450380676, https:\/\/doi.org\/10.1145\/3409256.3409829","DOI":"10.1145\/3409256.3409829"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Nogueira, R., Jiang, Z., Pradeep, R., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 708\u2013718, Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.63","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Nori, H., King, N., McKinney, S.M., Carignan, D., Horvitz, E.: Capabilities of GPT-4 on Medical Challenge Problems (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.13375","DOI":"10.48550\/arXiv.2303.13375"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS \u201922, Red Hook, NY, USA. Curran Associates Inc. (2024). ISBN 9781713871088, https:\/\/doi.org\/10.5555\/3600270.3602281","DOI":"10.5555\/3600270.3602281"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Pradeep, R., Nogueira, R.F., Lin, J.: The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. CoRR (2021). https:\/\/doi.org\/10.48550\/arXiv.2101.05667","DOI":"10.48550\/arXiv.2101.05667"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Reynolds, L., McDonell, K.: Prompt programming for large language models: beyond the few-shot paradigm. In: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. CHI EA \u201921, New York, NY, USA. Association for Computing Machinery (2021). ISBN 9781450380959, https:\/\/doi.org\/10.1145\/3411763.3451760","DOI":"10.1145\/3411763.3451760"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Roegiest, A., Pinkosova, Z.: Generative information systems are great if you can read. In: Clough, P.D., Harvey, M., Hopfgartner, F. (eds.) Proceedings of the 2024 ACM SIGIR Conference on Human Information Interaction and Retrieval, CHIIR 2024, Sheffield, United Kingdom, March 10-14, 2024, pp. 165\u2013177. ACM (2024). https:\/\/doi.org\/10.1145\/3627508.3638345","DOI":"10.1145\/3627508.3638345"},{"key":"10_CR20","doi-asserted-by":"publisher","unstructured":"Sakai, T.: SWAN: A Generic Framework for Auditing Textual Conversational Systems. CoRR (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.08290","DOI":"10.48550\/arXiv.2305.08290"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.: ColBERTv2: Effective and efficient retrieval via lightweight late interaction. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, United States, pp. 3715\u20133734, Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.272","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Wester, J., Lee, M., van Berkel, N.: Moral transparency as a mitigator of moral bias in conversational user interfaces. In: Proceedings of the 5th International Conference on Conversational User Interfaces, CUI \u201923, New York, NY, USA. Association for Computing Machinery (2023). ISBN 9798400700149, https:\/\/doi.org\/10.1145\/3571884.3603752","DOI":"10.1145\/3571884.3603752"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Xu, F., Song, Y., Iyyer, M., Choi, E.: A critical evaluation of evaluations for long-form question answering. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada, pp. 3225\u20133245. Association for Computational Linguistics (2023), https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.181","DOI":"10.18653\/v1\/2023.acl-long.181"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88714-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:42:22Z","timestamp":1743853342000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88714-7_10"}},"subtitle":["On the Agreement of Retrieval Models with Humans on Consumer Health Questions"],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887130","9783031887147"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88714-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"4 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lucca","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2025.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}