{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T02:09:29Z","timestamp":1789956569349,"version":"4.0.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031560682","type":"print"},{"value":"9783031560699","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56069-9_63","type":"book-chapter","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T04:17:45Z","timestamp":1711081065000},"page":"459-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ELOQUENT CLEF Shared Tasks for\u00a0Evaluation of\u00a0Generative Language Model Quality"],"prefix":"10.1007","author":[{"given":"Jussi","family":"Karlgren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luise","family":"D\u00fcrlich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelia","family":"Gogoulou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liane","family":"Guillou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joakim","family":"Nivre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magnus","family":"Sahlgren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aarne","family":"Talman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,23]]},"reference":[{"key":"63_CR1","doi-asserted-by":"crossref","unstructured":"Altinisik, E., Sajjad, H., Sencar, H.T., Messaoud, S., Chawla, S.: Impact of adversarial training on robustness and generalizability of language models. arXiv preprint arXiv:2211.05523 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.496"},{"key":"63_CR2","doi-asserted-by":"crossref","unstructured":"Bell, A.: Language style as audience design. Lang. Soc. 13(2) (1984)","DOI":"10.1017\/S004740450001037X"},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Bevendorff, J., et al.: Overview of PAN 2024: multi-author writing style analysis, multilingual text detoxification, oppositional thinking analysis, and generative AI authorship verification. In: Advances in Information Retrieval: 46th European Conference on IR Research (ECIR) (2024)","DOI":"10.1007\/978-3-031-56072-9_1"},{"key":"63_CR4","doi-asserted-by":"crossref","unstructured":"Bevendorff, J., et al.: Overview of PAN 2021: authorship verification, profiling hate speech spreaders on twitter, and style change detection. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction \u2013 12th International Conference of the CLEF Association (2021)","DOI":"10.1007\/978-3-030-85251-1_26"},{"key":"63_CR5","doi-asserted-by":"crossref","unstructured":"Bevendorff, J., et al.: Overview of PAN 2020: authorship verification, celebrity profiling, profiling fake news spreaders on twitter, and style change detection. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction \u2013 11th International Conference of the CLEF Association (2020)","DOI":"10.1007\/978-3-030-58219-7_25"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Ettinger, A., Rao, S., Daum\u00e9 III, H., Bender, E.M.: Towards linguistically generalizable NLP systems: a workshop and shared task. In: Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/W17-5401"},{"key":"63_CR7","unstructured":"Freitag, M., et al.: Results of WMT22 metrics shared task: stop using BLEU - neural metrics are better and more robust. In: Proceedings of the Seventh Conference on Machine Translation (WMT). Association for Computational Linguistics (2022)"},{"key":"63_CR8","doi-asserted-by":"crossref","unstructured":"Karlgren, J.: Adopting systematic evaluation benchmarks in operational settings. In: Information Retrieval Evaluation in a Changing World: Lessons Learned from 20 Years of CLEF (2019)","DOI":"10.1007\/978-3-030-22948-1_25"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Karlgren, J., et al.: Evaluating learning language representations. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction \u2013 6th International Conference of the CLEF Association (2015)","DOI":"10.1007\/978-3-319-24027-5_25"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Manakul, P., Liusie, A., Gales, M.J.F.: Selfcheckgpt: zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"63_CR11","doi-asserted-by":"crossref","unstructured":"Moradi, M., Samwald, M.: Evaluating the robustness of neural language models to input perturbations. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.117"},{"key":"63_CR12","unstructured":"M\u00fcndler, N., He, J., Jenko, S., Vechev, M.: Self-contradictory hallucinations of large language models: evaluation, detection and mitigation. arXiv preprint arXiv:2305.15852 (2023)"},{"key":"63_CR13","doi-asserted-by":"crossref","unstructured":"Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., Kiela, D.: Adversarial NLI: a new benchmark for natural language understanding. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"63_CR14","doi-asserted-by":"publisher","unstructured":"Sarvazyan, A.M., Gonz\u00e1lez, J.\u00c1., Rosso, P., Franco-Salvador, M.: Supervised machine-generated text detectors: family and scale matters. In: Arampatzis, A., et al. (eds.) Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2023. LNCS, vol. 14163, pp. 121\u2013132. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-42448-9_11","DOI":"10.1007\/978-3-031-42448-9_11"},{"key":"63_CR15","unstructured":"Saunders, W., et al..: Self-critiquing models for assisting human evaluators. arXiv preprint arXiv:2206.05802 (2022)"},{"key":"63_CR16","doi-asserted-by":"crossref","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. Nature 620(7972) (2023)","DOI":"10.1038\/s41586-023-06291-2"},{"key":"63_CR17","unstructured":"Stamatatos, E., et al.: Overview of the authorship verification task at PAN 2022. In: Faggioli, G., Ferro, N., Hanbury, A., Potthast, M. (eds.) CLEF 2022 Labs and Workshops, Notebook Papers. CEUR-WS.org (2022)"},{"key":"63_CR18","doi-asserted-by":"crossref","unstructured":"Stamatatos, E., Potthast, M., Pardo, F.M.R., Rosso, P., Stein, B.: Overview of the PAN\/CLEF 2015 evaluation lab. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction \u2013 6th International Conference of the CLEF Association (2015)","DOI":"10.1007\/978-3-319-24027-5_49"},{"key":"63_CR19","unstructured":"Wang, B., et al.: InfoBERT: improving robustness of language models from an information theoretic perspective. In: International Conference on Learning Representations (2021)"},{"key":"63_CR20","unstructured":"Wu, S., et al.: Bloomberggpt: a large language model for finance. arXiv preprint arXiv:2303.17564 (2023)"},{"key":"63_CR21","unstructured":"Zheng, C., Zhou, H., Meng, F., Zhou, J., Huang, M.: Large language models are not robust multiple choice selectors. arXiv preprint arXiv:2309.03882 (2023)"}],"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\/978-3-031-56069-9_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T04:31:13Z","timestamp":1711081873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56069-9_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560682","9783031560699"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56069-9_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"23 March 2024","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"578","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":"110","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":"69","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":"19% - 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":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","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)"}}]}}