{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:08:50Z","timestamp":1774310930794,"version":"3.50.1"},"publisher-location":"Cham","reference-count":16,"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_36","type":"book-chapter","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:08:08Z","timestamp":1774264088000},"page":"259-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ELOQUENT Lab at\u00a0CLEF 2026: Evaluation of\u00a0Generative Language Model Quality"],"prefix":"10.1007","author":[{"given":"Jussi","family":"Karlgren","sequence":"first","affiliation":[]},{"given":"Maria","family":"Barrett","sequence":"additional","affiliation":[]},{"given":"Ond\u0159ej","family":"Bojar","sequence":"additional","affiliation":[]},{"given":"Marie Isabel","family":"Engels","sequence":"additional","affiliation":[]},{"given":"Diandra","family":"Fabre","sequence":"additional","affiliation":[]},{"given":"Lorraine","family":"Goeuriot","sequence":"additional","affiliation":[]},{"given":"Josiane","family":"Mothe","sequence":"additional","affiliation":[]},{"given":"Philippe","family":"Mulhem","sequence":"additional","affiliation":[]},{"given":"Mario","family":"Piacentini","sequence":"additional","affiliation":[]},{"given":"Luis Francisco Vargas","family":"Madriz","sequence":"additional","affiliation":[]},{"given":"Didier","family":"Schwab","sequence":"additional","affiliation":[]},{"given":"Pavel","family":"\u0160indel\u00e1\u0159","sequence":"additional","affiliation":[]},{"given":"Georgios","family":"Stampoulidis","sequence":"additional","affiliation":[]},{"given":"Katherina","family":"Thomas","sequence":"additional","affiliation":[]},{"given":"Markarit","family":"Vartampetian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"36_CR1","unstructured":"Barrett, M., Stampoulidis, G., Zautner, D., Burdge, J., Karlgren, J.: Measuring the cultural capabilities of LLMs across European languages. In: Under Review (2025)"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Bavaresco, A., et al.: LLMs instead of Human Judges? a large scale empirical study across 20 NLP evaluation tasks (2024)","DOI":"10.18653\/v1\/2025.acl-short.20"},{"key":"36_CR3","unstructured":"Bevendorff, J., et al.: Overview of the \u201cVoight-Kampff\u201d generative AI authorship verification task at PAN and ELOQUENT 2025. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2025). CEUR-WS (2025)"},{"key":"36_CR4","unstructured":"Bevendorff, J., et al.: Overview of the \u201cVoight-Kampff\u201d generative AI authorship verification task at PAN and ELOQUENT 2024. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2024), vol. 3740. CEUR-WS (2024)"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Doddapaneni, S., Khan, M.S.U.R., Verma, S., Khapra, M.M.: Finding blind spots in evaluator LLMS with interpretable checklists (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.911"},{"key":"36_CR6","unstructured":"D\u00fcrlich, L., Gogoulou, E., Guillou, L., Nivre, J., Zahra, S.: Overview of the CLEF-2024 eloquent lab: task 2 on HalluciGen. In: Faggioli, G., Ferro, N., Vlachos, M., Galu\u0161\u010d\u00e1kov\u00e1, P., Garc\u00eda\u00a0Seco de\u00a0Herrera, A., (eds), Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum. CEUR-WS.org (2024)"},{"key":"36_CR7","unstructured":"Hui, H., Qu, Y., Zhou, H., Liu, J., Yang, M., Xu, B., Zhao, T.: On the limitations of fine-tuned judge models for LLM evaluation (2024)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Karlgren, J., et al.: Overview of ELOQUENT 2025: shared tasks for evaluating generative language model quality. In: International Conference of the Cross-Language Evaluation Forum for European Languages. Springer (2025)","DOI":"10.1007\/978-3-032-04354-2_14"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Karlgren, J., et al.: Overview of ELOQUENT 2024\u2014shared tasks for evaluating generative language model quality. In: Goeuriot, L., et al., (eds), Experimental IR Meets Multilinguality, Multimodality, and Interaction \u2013 Proceedings of the 15th International Conference of the CLEF Association (2024)","DOI":"10.1007\/978-3-031-71908-0_3"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Karlgren, J., et al.: Overview and joint report of the robustness and consistency task at the ELOQUENT 2025 lab for evaluating generative language model quality. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2025). CEUR-WS (2025)","DOI":"10.1007\/978-3-032-04354-2_14"},{"key":"36_CR11","unstructured":"Karlgren, J., Talman, A.: ELOQUENT 2024 \u2014 topical quiz task. In: Faggioli, G., Ferro, N., Vlachos, M., Galu\u0161\u010d\u00e1kov\u00e1, P., Garc\u00eda\u00a0Seco de\u00a0Herrera, A., (eds), Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum. CEUR-WS.org (2024)"},{"key":"36_CR12","unstructured":"Mikhailov, V., Artemova, E., Butenko, Z., \u00d8vrelid, L., Velldal, Z.: Overview of the preference prediction task at the ELOQUENT 2025 lab for evaluating generative language model quality. In: Faggioli, G., Ferro, N., Rosso, P., Spina, D., (eds), Working Notes of CLEF 2025 \u2013 Conference and Labs of the Evaluation Forum. CEUR-WS (2025)"},{"key":"36_CR13","unstructured":"OECD. PISA 2022 Technical Report. OECD Publishing, Paris (2024)"},{"key":"36_CR14","unstructured":"Sahlgren, M., Karlgren, J., D\u00fcrlich, L., Gogoulou, E., Talman, A., Zahra, S.: Eloquent 2024\u2014robustness task. In: Faggioli, G., Ferro, N., Vlachos, M., Galu\u0161\u010d\u00e1kov\u00e1, P., Garc\u00eda\u00a0Seco de\u00a0Herrera, A. (eds.) Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum. CEUR-WS.org (2024)"},{"key":"36_CR15","unstructured":"V\u00e1zquez, R., et\u00a0al.: Semeval-2025 task 3: mu-shroom, the multilingual shared task on hallucinations and related observable overgeneration mistakes. arXiv preprint arXiv:2504.11975 (2025)"},{"key":"36_CR16","unstructured":"Verga, P., et al.: Replacing judges with juries: Evaluating LLM generations with a panel of diverse models (2024)"}],"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_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:13:41Z","timestamp":1774307621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21321-1_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032213204","9783032213211"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21321-1_36","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":"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"}}]}}