{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:10:56Z","timestamp":1774311056994,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032213204","type":"print"},{"value":"9783032213211","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-21321-1_21","type":"book-chapter","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:10:22Z","timestamp":1774264222000},"page":"148-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Talmud-IR: A Talmud-Inspired Interface for\u00a0Discussing RAG Response Quality"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4420-4147","authenticated-orcid":false,"given":"Wojciech","family":"Kusa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6803-1223","authenticated-orcid":false,"given":"Niklas","family":"Deckers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1003-981X","authenticated-orcid":false,"given":"Maik","family":"Fr\u00f6be","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1624-3907","authenticated-orcid":false,"given":"Laura","family":"Dietz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1738-8302","authenticated-orcid":false,"given":"Birte","family":"Platow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0487-9609","authenticated-orcid":false,"given":"Mark","family":"Sanderson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Amsler, M.: The Babylonian Talmud and Late Antique Book Culture. Cambridge University Press, Cambridge (2023)","DOI":"10.1017\/9781009297349"},{"key":"21_CR2","unstructured":"Cheng, M., Yu, S., Lee, C., Khadpe, P., Ibrahim, L., Jurafsky, D.: Social sycophancy: a broader anderstanding of LLM sycophancy. arXiv preprint arXiv:2505.13995 (2025)"},{"key":"21_CR3","unstructured":"Clarke, C.L., Dietz, L.: Support evaluation for the TREC 2024 RAG track: comparing human versus LLM judges. arXiv preprint arXiv:2504.15205 (2025)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Di\u00a0Palma, D., Merra, F.A., Sfilio, M., Anelli, V.W., Narducci, F., Di\u00a0Noia, T.: Do llms memorize recommendation datasets? a preliminary study on movielens-1m. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2582\u20132586 (2025)","DOI":"10.1145\/3726302.3730178"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Dietz, L., et al.: Principles and guidelines for the use of llm judges. In: Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR), pp. 218\u2013229 (2025)","DOI":"10.1145\/3731120.3744588"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Es, S., James, J., Anke, L.E., 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)","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"21_CR7","doi-asserted-by":"crossref","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, pp. 175\u2013184 (2024)","DOI":"10.1145\/3664190.3672511"},{"issue":"3","key":"21_CR8","first-page":"317","volume":"45","author":"R Fok","year":"2024","unstructured":"Fok, R., Weld, D.S.: In search of verifiability: explanations rarely enable complementary performance in ai-advised decision making. AI Mag. 45(3), 317\u2013332 (2024)","journal-title":"AI Mag."},{"key":"21_CR9","unstructured":"Fr\u00f6be, M., et al.: Webis at TREC 2024: biomedical generative retrieval, retrieval-augmented generation, and tip-of-the-tongue tracks. In: Voorhees, E., Ellis, A. (eds.) 33th International Text Retrieval Conference (TREC 2024), NIST Special Publication, National Institute of Standards and Technology (NIST) (2024). https:\/\/trec.nist.gov\/pubs\/trec33\/index.html"},{"key":"21_CR10","unstructured":"Kraemer, D.C.: A History of the Talmud. Cambridge University Press, Cambridge (2019)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Lin, J., Demner-Fushman, D.: Will pyramids built of nuggets topple over? In: Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pp. 383\u2013390 (2006)","DOI":"10.3115\/1220835.1220884"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Mayfield, J., et\u00a0al.: On the evaluation of machine-generated reports. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1904\u20131915 (2024)","DOI":"10.1145\/3626772.3657846"},{"key":"21_CR13","doi-asserted-by":"publisher","unstructured":"Pradeep, R., et al.: Ragnar\u00f6k: a reusable RAG framework and baselines for TREC 2024 retrieval-augmented generation track. In: Hauff, C., Macdonald, C., Jannach, D., Kazai, G., Nardini, F.M., Pinelli, F., Silvestri, F., Tonellotto, N. (eds.) Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6-10, 2025, Proceedings, Part I, Lecture Notes in Computer Science, vol. 15572, pp. 132\u2013148, Springer, Cham (2025), https:\/\/doi.org\/10.1007\/978-3-031-88708-6_9","DOI":"10.1007\/978-3-031-88708-6_9"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Pradeep, R., et al.: The great nugget recall: automating fact extraction and rag evaluation with large language models. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 180\u2013190 (2025)","DOI":"10.1145\/3726302.3730090"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Saad-Falcon, J., Khattab, O., Potts, C., Zaharia, M.: ARES: an automated evaluation framework for retrieval-augmented generation systems. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 338\u2013354 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.20"},{"key":"21_CR16","unstructured":"Sander, D.P., Dietz, L.: Exam: how to evaluate retrieve-and-generate systems for users who do not (yet) know what they want. In: DESIRES, pp. 136\u2013146 (2021)"},{"key":"21_CR17","doi-asserted-by":"publisher","unstructured":"Thakur, N., Pradeep, R., Upadhyay, S., Campos, D., Craswell, N., Lin, J.: Support evaluation for the TREC 2024 RAG track: comparing human versus LLM judges. CoRR abs\/2504.15205 (2025). https:\/\/doi.org\/10.48550\/ARXIV.2504.15205","DOI":"10.48550\/ARXIV.2504.15205"},{"key":"21_CR18","unstructured":"Upadhyay, S., Pradeep, R., Thakur, N., Craswell, N., Lin, J.: Umbrela: umbrela is the (open-source reproduction of the) bing relevance assessor. arXiv preprint arXiv:2406.06519 (2024)"},{"key":"21_CR19","unstructured":"Walden, W., et al.: Auto-argue: Llm-based report generation evaluation. arXiv preprint arXiv:2509.26184 (2025)"},{"key":"21_CR20","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L.: Judging llm-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"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\/978-3-032-21321-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:17:06Z","timestamp":1774307826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21321-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032213204","9783032213211"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21321-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"24 March 2026","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":"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":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}