{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:33:17Z","timestamp":1774308797898,"version":"3.50.1"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887192","type":"print"},{"value":"9783031887208","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\/978-3-031-88720-8_23","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T12:09:31Z","timestamp":1743768571000},"page":"135-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RURAGE: Robust Universal RAG Evaluator for\u00a0Fast and\u00a0Affordable QA Performance Testing"],"prefix":"10.1007","author":[{"given":"Nikita","family":"Krayko","sequence":"first","affiliation":[]},{"given":"Ivan","family":"Sidorov","sequence":"additional","affiliation":[]},{"given":"Fedor","family":"Laputin","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Panchenko","sequence":"additional","affiliation":[]},{"given":"Daria","family":"Galimzianova","sequence":"additional","affiliation":[]},{"given":"Vasily","family":"Konovalov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","unstructured":"Adlakha, V., BehnamGhader, P., Lu, X.H., Meade, N., Reddy, S.: Evaluating correctness and faithfulness of instruction-following models for question answering. Trans. Assoc. Comput. Linguistics 12, 681\u2013699 (2024). https:\/\/doi.org\/10.1162\/TACL_A_00667","DOI":"10.1162\/TACL_A_00667"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Belikova, J., Beliakin, E., Konovalov, V.: JellyBell at TextGraphs-17 shared task: fusing large language models with external knowledge for enhanced question answering. In: Ustalov, D., et al. (eds.) Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing, pp. 154\u2013160. Association for Computational Linguistics, Bangkok, Thailand (Aug 2024). https:\/\/aclanthology.org\/2024.textgraphs-1.15\/","DOI":"10.18653\/v1\/2024.textgraphs-1.15"},{"key":"23_CR3","unstructured":"ES, S., James, J., Anke, L.E., Schockaert, S.: Ragas: Automated evaluation of retrieval augmented generation. In: Aletras, N., Clercq, O.D. (eds.) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - System Demonstrations, St. Julians, Malta, 17-22 March 2024, pp. 150\u2013158. Association for Computational Linguistics (2024). https:\/\/aclanthology.org\/2024.eacl-demo.16"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Fadeeva, E., Vashurin, R., Tsvigun, A., Vazhentsev, A., Petrakov, S., Fedyanin, K., Vasilev, D., Goncharova, E., Panchenko, A., Panov, M., Baldwin, T., Shelmanov, A.: LM-polygraph: uncertainty estimation for language models. In: Feng, Y., Lefever, E. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 446\u2013461. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-demo.41, https:\/\/aclanthology.org\/2023.emnlp-demo.41","DOI":"10.18653\/v1\/2023.emnlp-demo.41"},{"key":"23_CR5","unstructured":"Huang, Y., et al.: Look before you leap: An exploratory study of uncertainty measurement for large language models. arXiv preprint arXiv:2307.10236 (2023)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Krayko, N., Sidorov, I., Laputin, F., Galimzianova, D., Konovalov, V.: Efficient answer retrieval system (EARS): combining local DB search and web search for generative QA. In: Dernoncourt, F., Preo\u0163iuc-Pietro, D., Shimorina, A. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track. pp. 1584\u20131594. Association for Computational Linguistics, Miami, Florida, US (Nov 2024). https:\/\/aclanthology.org\/2024.emnlp-industry.116","DOI":"10.18653\/v1\/2024.emnlp-industry.116"},{"key":"23_CR7","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, NAACL-HLT 2021, Online, June 6-11, 2021. pp. 4940\u20134957. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/V1\/2021.NAACL-MAIN.393, https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.393","DOI":"10.18653\/V1\/2021.NAACL-MAIN.393"},{"key":"23_CR8","unstructured":"Laurer, M., Atteveldt, W.v., Casas, A.S., Welbers, K.: Less Annotating, More Classifying \u2013 Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT - NLI. Preprint (Jun 2022). https:\/\/osf.io\/74b8k, publisher: Open Science Framework"},{"key":"23_CR9","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out. pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (Jul 2004). https:\/\/aclanthology.org\/W04-1013\/"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Maksimov, I., Konovalov, V., Glinskii, A.: DeepPavlov at SemEval-2024 task 6: detection of hallucinations and overgeneration mistakes with an ensemble of transformer-based models. In: Ojha, A.K., Do\u011fru\u00f6z, A.S., Tayyar\u00a0Madabushi, H., Da\u00a0San\u00a0Martino, G., Rosenthal, S., Ros\u00e1, A. (eds.) Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024). pp. 274\u2013278. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.semeval-1.42, https:\/\/aclanthology.org\/2024.semeval-1.42\/","DOI":"10.18653\/v1\/2024.semeval-1.42"},{"key":"23_CR11","unstructured":"Nicole\u00a0Liu, S.K.: The futures too bright: Chatgpt\u2019s optimism forecasting bias. ICIS 2024 Proceedings (2024). https:\/\/aisel.aisnet.org\/cgi\/viewcontent.cgi?article=1248&context=icis2024"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 6-12 July 2002, Philadelphia, PA, USA, pp. 311\u2013318. ACL (2002). https:\/\/doi.org\/10.3115\/1073083.1073135, https:\/\/aclanthology.org\/P02-1040\/","DOI":"10.3115\/1073083.1073135"},{"key":"23_CR13","unstructured":"Prokhorenkova, L.O., Gusev, G., Vorobev, A., Dorogush, A.V., Gulin, A.: Catboost: unbiased boosting with categorical features. In: Bengio, S., Wallach, H.M., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montr\u00e9al, Canada, pp. 6639\u20136649 (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/14491b756b3a51daac41c24863285549-Abstract.html"},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., Wei, F.: Text embeddings by weakly-supervised contrastive pre-training. CoRR abs\/ arXiv: 2212.03533 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.03533","DOI":"10.48550\/ARXIV.2212.03533"},{"key":"23_CR15","unstructured":"Zhu, L., Wang, X., Wang, X.: Judgelm: Fine-tuned large language models are scalable judges (2023). https:\/\/arxiv.org\/abs\/2310.17631"}],"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\/978-3-031-88720-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T12:09:42Z","timestamp":1743768582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88720-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887192","9783031887208"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88720-8_23","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":"3 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"}}]}}