{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:07:55Z","timestamp":1774310875947,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"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_37","type":"book-chapter","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:12:34Z","timestamp":1774264354000},"page":"267-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The CLEF-2026 FinMMEval Lab: Multilingual and\u00a0Multimodal Evaluation of\u00a0Financial AI Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2650-2857","authenticated-orcid":false,"given":"Zhuohan","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9337-9680","authenticated-orcid":false,"given":"Rania","family":"Elbadry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7515-3542","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4418-7622","authenticated-orcid":false,"given":"Georgi","family":"Georgiev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1484-0622","authenticated-orcid":false,"given":"Xueqing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8342-1837","authenticated-orcid":false,"given":"Lingfei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3501-3907","authenticated-orcid":false,"given":"Jimin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1308-180X","authenticated-orcid":false,"given":"Dimitar","family":"Dimitrov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1292-7386","authenticated-orcid":false,"given":"Vanshikaa","family":"Jani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4077-0493","authenticated-orcid":false,"given":"Yuyang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4205-8230","authenticated-orcid":false,"given":"Jiahui","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-1826","authenticated-orcid":false,"given":"Yuxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3919-030X","authenticated-orcid":false,"given":"Ivan","family":"Koychev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1250-4820","authenticated-orcid":false,"given":"Veselin","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3600-1510","authenticated-orcid":false,"given":"Preslav","family":"Nakov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: FinQA: a dataset of numerical reasoning over financial data. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3697\u20133711 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, S., Smiley, C., Ma, Z., Shah, S., Wang, W.Y.: ConvFinQA: exploring the chain of numerical reasoning in conversational finance question answering. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6279\u20136292. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"37_CR3","unstructured":"Dai, Y., Lin, Y., Xie, Z., Wang, Y.: RealFin: how well do LLMs reason about finance when users leave things unsaid? preprint (2026)"},{"key":"37_CR4","unstructured":"Devane, V., et al.: BhashaBench-finance: benchmarking AI on Indian financial knowledge. https:\/\/huggingface.co\/datasets\/bharatgenai\/bhashabench-finance (2025), Accessed 14 Oct 2025"},{"key":"37_CR5","unstructured":"Elbadry, R., et al.: SAHM: a benchmark for Arabic financial and Shari\u2019ah-compliant reasoning. preprint (2026)"},{"key":"37_CR6","unstructured":"Feng, D., et al.: Empowering many, biasing a few: generalist credit scoring through large language models. arXiv preprint arXiv:2310.00566 (2023)"},{"key":"37_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/00036846.2025.2450384","volume":"57","author":"O Hean","year":"2025","unstructured":"Hean, O., Saha, U., Saha, B.: Can AI help with your personal finances? Appl. Econ. 57, 1\u20139 (2025)","journal-title":"Appl. Econ."},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Kaur, S., et al.: REFinD: relation extraction financial dataset. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3054\u20133063 (2023)","DOI":"10.1145\/3539618.3591911"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Koncel-Kedziorski, R., Krumdick, M., Lai, V., Reddy, V., Lovering, C., Tanner, C.: BizBench: a quantitative reasoning benchmark for business and finance. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8309\u20138332 (2024)","DOI":"10.18653\/v1\/2024.acl-long.452"},{"key":"37_CR10","unstructured":"Liu, X.Y., Wang, G., Yang, H., Zha, D.: FinGPT: democratizing internet-scale data for financial large language models. arXiv preprint arXiv:2307.10485 (2023)"},{"key":"37_CR11","unstructured":"Liu, Z., et al.: FinNLP-FNP-LLMFinLegal-2025 shared task: financial misinformation detection challenge task. In: Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing, the 6th Financial Narrative Processing, and the 1st Workshop on Large Language Models for Finance and Legal, pp. 271\u2013276 (2025)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, D., Huang, K., Li, Z., Zhao, J.: FinBERT: a pre-trained financial language representation model for financial text mining. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. IJCAI\u201920 (2021)","DOI":"10.24963\/ijcai.2020\/622"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Maia, M., et al.: WWW\u201918 open challenge: financial opinion mining and question answering. In: Companion Proceedings of The Web Conference 2018, pp. 1941\u20131942 (2018)","DOI":"10.1145\/3184558.3192301"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Malaysha, S., et al.: AraFinNLP 2024: the first Arabic financial NLP shared task. In: Proceedings of the Second Arabic Natural Language Processing Conference, pp. 393\u2013402 (2024)","DOI":"10.18653\/v1\/2024.arabicnlp-1.34"},{"key":"37_CR15","unstructured":"Mariko, D., Abi-Akl, H., Labidurie, E., Durfort, S., De\u00a0Mazancourt, H., El-Haj, M.: The financial document causality detection shared task (FinCausal 2020). In: Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pp. 23\u201332 (2020)"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Mukherjee, R., et al.: ECTSum: a new benchmark dataset for bullet point summarization of long earnings call transcripts. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 10893\u201310906. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.748"},{"key":"37_CR17","unstructured":"Nararatwong, R., Kertkeidkachorn, N., Takamura, H., Ichise, R.: Fin-DBQA shared-task: database querying and reasoning. In: Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing, the 6th Financial Narrative Processing, and the 1st Workshop on Large Language Models for Finance and Legal, pp. 385\u2013391 (2025)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Nie, Y., et al.: CFinBench: a comprehensive Chinese financial benchmark for large language models. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 876\u2013891 (2025)","DOI":"10.18653\/v1\/2025.naacl-long.40"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Peng, X., et al.: Plutus: benchmarking large language models in low-resource Greek finance. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 30176\u201330202 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1535"},{"key":"37_CR20","unstructured":"Peng, X., et al.: MultiFinBen: a multilingual, multimodal, and difficulty-aware benchmark for financial LLM evaluation. arXiv preprint arXiv:2506.14028 (2025)"},{"key":"37_CR21","unstructured":"Shah, A., Gullapalli, A., Vithani, R., Galarnyk, M., Chava, S.: FiNER-ORD: financial named entity recognition open research dataset. arXiv preprint arXiv:2302.11157 (2023)"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Shah, R.S., et al.: When FLUE meets FLANG: benchmarks and large pre-trained language model for financial domain. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 2322\u20132335 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.148"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Takayanagi, T., Goldsack, T., Izumi, K., Lin, C., Takamura, H., Chen, C.C.: Earnings2Insights: analyst report generation for investment guidance. In: Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing, pp. 246\u2013251 (2025)","DOI":"10.18653\/v1\/2025.finnlp-2.17"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yang, Y.: FinMTEB: finance massive text embedding benchmark. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 3620\u20133638 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.179"},{"key":"37_CR25","unstructured":"Wang, K., et al.: FinNLP-FNP-LLMFinLegal-2025 shared task: regulations challenge. In: Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing, the 6th Financial Narrative Processing, and the 1st Workshop on Large Language Models for Finance and Legal, pp. 363\u2013370 (2025)"},{"key":"37_CR26","unstructured":"Wu, S., et al.: BloombergGPT: a large language model for finance. arXiv preprint arXiv:2303.17564 (2023)"},{"key":"37_CR27","unstructured":"Xie, Q., et al.: FinBen: a holistic financial benchmark for large language models. In: Advances in Neural Information Processing Systems. vol.\u00a037 (2024)"},{"key":"37_CR28","unstructured":"Xie, Q., et al.: PIXIU: a large language model, instruction data and evaluation benchmark for finance. arXiv preprint arXiv:2306.05443 (2023)"},{"key":"37_CR29","unstructured":"Xie, Q., et al.: FinNLP-AgentScen-2024 shared task: financial challenges in large language models - FinLLMs. In: Proceedings of the Eighth Financial Technology and Natural Language Processing and the 1st Agent AI for Scenario Planning, pp. 119\u2013126 (2024)"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Xie, Z., Cohn, T., Lau, J.H.: The next chapter: a study of large language models in storytelling. In: Proceedings of the 16th International Natural Language Generation Conference, pp. 323\u2013351 (2023)","DOI":"10.18653\/v1\/2023.inlg-main.23"},{"key":"37_CR31","unstructured":"Xie, Z., et al.: FinChain: a symbolic benchmark for verifiable chain-of-thought financial reasoning. arXiv preprint arXiv:2506.02515 (2026)"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: FIRE: fact-checking with iterative retrieval and verification. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 2901\u20132914 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.158"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Yuan, T., et al.: R-Judge: benchmarking safety risk awareness for LLM agents. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 1467\u20131490 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.79"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: D\u00f3lares or dollars? unraveling the bilingual prowess of financial LLMs between Spanish and English. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 6236\u20136246 (2024)","DOI":"10.1145\/3637528.3671554"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Liu, H., Long, Y., Zhang, R., Zhao, C., Cohan, A.: FinanceMATH: knowledge-intensive math reasoning in finance domains. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12841\u201312858 (2024)","DOI":"10.18653\/v1\/2024.acl-long.693"},{"key":"37_CR36","unstructured":"Zhou, Y., Zhang, F., Chen, Y., Zhang, H., Nakov, P., Xie, Z.: FinCARDS: card-based analyst reranking for financial document question answering. arXiv preprint arXiv:2601.06992 (2026)"},{"key":"37_CR37","doi-asserted-by":"publisher","unstructured":"TZhu, F., et al.: TATQA: a question answering benchmark on a hybrid of tabular and textual content in finance. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3277\u20133287 (2021). https:\/\/doi.org\/10.1007\/978-981-16-1357-9_3","DOI":"10.1007\/978-981-16-1357-9_3"}],"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_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:12:24Z","timestamp":1774307544000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21321-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032213204","9783032213211"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21321-1_37","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"}}]}}