{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:22:29Z","timestamp":1787404949953,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540907","type":"print"},{"value":"9789819540914","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4091-4_17","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T20:07:59Z","timestamp":1762632479000},"page":"244-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FinLBench: A Benchmark for\u00a0Evaluating Large Language Models on\u00a0Long-Text Financial Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0865-1768","authenticated-orcid":false,"given":"Sihan","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8640-7551","authenticated-orcid":false,"given":"Dingfu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5597-2554","authenticated-orcid":false,"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8027-9560","authenticated-orcid":false,"given":"Zhongliang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0727-2436","authenticated-orcid":false,"given":"Linna","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5731-5312","authenticated-orcid":false,"given":"Xinguang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5528-7606","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9719-1147","authenticated-orcid":false,"given":"Binjie","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8058-0649","authenticated-orcid":false,"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"17_CR1","unstructured":"Achiam, J., et al.: GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"17_CR2","unstructured":"An, C., et al.: L-eval: Instituting Standardized Evaluation for Long Context Language Models. arXiv preprint arXiv:2307.11088 (2023)"},{"key":"17_CR3","unstructured":"Bai, Y., et al.: Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508 (2023)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Bai, G., et al.: Mt-bench-101: A fine-grained benchmark for evaluating large language models in multi-turn dialogues. arXiv preprint arXiv:2402.14762 (2024)","DOI":"10.18653\/v1\/2024.acl-long.401"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Bhatia, G., Nagoudi, E. M. B., Cavusoglu, H., Abdul-Mageed, M.: Fintral: A Family of GPT-4 Level Multimodal Financial Large Language Models. arXiv preprint arXiv:2402.10986 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.774"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 17709\u201317717. AAAI Press (2024)","DOI":"10.1609\/aaai.v38i16.29723"},{"key":"17_CR7","unstructured":"Cui, J., Li, Z., Yan, Y., Chen, B., Yuan, L.: ChatLaw: Open Source Legal Large Language Model with Integrated External Knowledge Bases. arXiv preprint arXiv:2306.16092 (2023)"},{"key":"17_CR8","unstructured":"Dai, Y., et al.: LAiW: A Chinese Legal Large Language Models Benchmark (A Technical Report). arXiv preprint arXiv:2310.05620 (2023)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Desmond, M., Ashktorab, Z., Pan, Q., Dugan, C., Johnson, J. M.: EvaluLLM: LLM Assisted evaluation of generative outputs. In: Companion Proceedings of the 29th International Conference on Intelligent User Interfaces, pp. 30\u201332 (2024)","DOI":"10.1145\/3640544.3645216"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Dong, Z., Tang, T., Li, J., Zhao, W. X., Wen, J.-R.: Bamboo: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models. arXiv preprint arXiv:2309.13345 (2023)","DOI":"10.63317\/3knkq4fwny8w"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Fei, Z., et al.: Lawbench: Benchmarking legal knowledge of large language models. arXiv preprint arXiv:2309.16289 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.452"},{"key":"17_CR12","unstructured":"Fei, Z., et al.: InternLM-Law: An Open Source Chinese Legal Large Language Model. arXiv preprint arXiv:2406.14887 (2024)"},{"key":"17_CR13","unstructured":"GLM Team, Zeng, A., et al.: ChatGLM: A family of large language models from GLM-130B to GLM-4 with all tools. arXiv preprint arXiv:2406.12793 (2024)"},{"key":"17_CR14","unstructured":"Hu, G., et al.: No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks. arXiv preprint arXiv:2403.06249 (2024)"},{"key":"17_CR15","unstructured":"Islam, P., Kannappan, A., Kiela, D., Qian, R., Scherrer, N., Vidgen, B.: FinanceBench: A New Benchmark for Financial Question Answering. arXiv preprint arXiv:2311.11944 (2023)"},{"key":"17_CR16","unstructured":"Kraljevic, Z., Shek, A., Bean, D., Bendayan, R., Teo, J., Dobson, R.: MedGPT: Medical Concept Prediction from Clinical Narratives. arXiv preprint arXiv:2107.03134 (2021)"},{"key":"17_CR17","unstructured":"Lei, Y., et al.: CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model. arXiv preprint arXiv:2311.05812 (2023)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, M., Zheng, Z., Zhang, M.: LooGLE: Can Long-Context Language Models Understand Long Contexts? arXiv preprint arXiv:2311.04939 (2023)","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: CFGPT: Chinese Financial Assistant with Large Language Model. arXiv preprint arXiv:2309.10654 (2023)","DOI":"10.1007\/s11704-024-31018-5"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Lin, Y.-T., Chen, Y.-N.: LLM-Eval: Unified multi-dimensional automatic evaluation for open-domain conversations with large language models. arXiv preprint arXiv:2305.13711 (2023)","DOI":"10.18653\/v1\/2023.nlp4convai-1.5"},{"key":"17_CR21","unstructured":"Lu, D., et al.: BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-Trained Language Model, Corpus and Benchmark. arXiv preprint arXiv:2302.09432 (2023)"},{"key":"17_CR22","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":"17_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety. arXiv preprint arXiv:2403.12316 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.19"},{"key":"17_CR24","unstructured":"Liu, M., et al.: Large Language Models. arXiv preprint arXiv:2407.10990 (2024)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Shah, R., et al.: When FLUE Meets FLANG: benchmarks and large pretrained language model for financial domain. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 2322\u20132335. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.148"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Shaham, U., Ivgi, M., Efrat, A., others: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 7977\u20137989. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.536"},{"key":"17_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108290","volume":"172","author":"Y Tan","year":"2024","unstructured":"Tan, Y., et al.: others: MedChatZH: a tuning LLM for traditional Chinese medicine consultations. Comput. Biol. Med. 172, 108290 (2024)","journal-title":"Comput. Biol. Med."},{"key":"17_CR28","unstructured":"Wang, Z., Li, Y., Wu, J., Soon, J., Zhang, X.: FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis. arXiv preprint arXiv:2308.01430 (2023)"},{"key":"17_CR29","unstructured":"Wu, S., et al.: BloombergGPT: A Large Language Model for Finance. arXiv preprint arXiv:2303.17564 (2023)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Xie, Q., et al.: Pixiu: A comprehensive benchmark, instruction dataset and large language model for finance. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-1454"},{"key":"17_CR31","unstructured":"Xie, Q., et al.: The finben: An holistic financial benchmark for large language models. arXiv preprint arXiv:2402.12659 (2024)"},{"key":"17_CR32","unstructured":"Xu, Z., Jain, S., Kankanhalli, M.: Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv:2401.11817 (2024)"},{"key":"17_CR33","unstructured":"Yang, A., et al.: Qwen2 Technical Report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Yu, Y., et al.: FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making. arXiv preprint arXiv:2407.06567 (2024)","DOI":"10.52202\/079017-4354"},{"key":"17_CR35","unstructured":"Zhang, L., et al.: Fineval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models. arXiv preprint arXiv:2308.09975 (2023)"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In: Advances in Neural Information Processing Systems, vol.\u00a036. (2024)","DOI":"10.52202\/075280-2020"},{"key":"17_CR37","unstructured":"Zhou, Z., et al.: LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model. arXiv preprint arXiv:2406.04614 (2024)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4091-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T12:28:25Z","timestamp":1787401705000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4091-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819540907","9789819540914"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4091-4_17","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","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","label":"Disclosure of Interest","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}