{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:42:50Z","timestamp":1762843370845,"version":"build-2065373602"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04497-x","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:38:42Z","timestamp":1762843122000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models Acing Chartered Accountancy"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9504-7487","authenticated-orcid":false,"given":"Jatin","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1490-4022","authenticated-orcid":false,"given":"Akhil","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6925-001X","authenticated-orcid":false,"given":"Saransh","family":"Singhania","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4134-0277","authenticated-orcid":false,"given":"Mohammad","family":"Adnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4528-2680","authenticated-orcid":false,"given":"Sakshi","family":"Deo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7420-0027","authenticated-orcid":false,"given":"Ali Imam","family":"Abidi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7851-1976","authenticated-orcid":false,"given":"Keshav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"4497_CR1","unstructured":"Feyen E, Frost J, Gambacorta L, Natarajan H, Saal M. Fintech and the digital transformation of financial services: implications for market structure and public policy. BIS papers 2021."},{"key":"4497_CR2","unstructured":"Financial Services Industry: IT Market Size & Trends Report. https:\/\/hginsights.com\/market-reports\/financial-services-industry"},{"key":"4497_CR3","unstructured":"Financial Services Market Report 2025 - Research and Markets. https:\/\/www.researchandmarkets.com\/reports\/5939673\/financial-services-market-report"},{"key":"4497_CR4","doi-asserted-by":"publisher","unstructured":"Xu T, MacDonald M. Financial sector and economic growth in india. IMF Working Papers 2022;2022, (1) https:\/\/doi.org\/10.5089\/9798400216404.001","DOI":"10.5089\/9798400216404.001"},{"key":"4497_CR5","unstructured":"ICAI - The Institute of Chartered Accountants of India. https:\/\/www.icai.org\/overview.shtml"},{"key":"4497_CR6","unstructured":"Bommasani R, Hudson DA, Adeli E, Altman R, Arora S, Arx S, Bernstein MS, Bohg J, Bosselut A., Brunskill E, Brynjolfsson E, Buch S, Card D, Castellon R, Chatterji N, Chen A, Creel K, Davis JQ, Demszky D, Donahue C, Doumbouya M, Durmus E, Ermon S, Etchemendy J, Ethayarajh K, Fei-Fei L, Finn C, Gale T, Gillespie L, Goel K, Goodman N, Grossman S, Guha N, Hashimoto T, Henderson P, Hewitt J, Ho DE, Hong J, Hsu K, Huang J, Icard T, Jain S, Jurafsky D, Kalluri P, Karamcheti S, Keeling G, Khani F, Khattab O, Koh PW, Krass M, Krishna R, Kuditipudi R, Kumar A, Ladhak F, Lee M, Lee T, Leskovec J, Levent I, Li XL, Li X, Ma T, Malik A, Manning CD, Mirchandani S, Mitchell E, Munyikwa Z, Nair S, Narayan A, Narayanan D, Newman B, Nie A, Niebles JC, Nilforoshan, H, Nyarko J, Ogut G., Orr L., Papadimitriou I, Park JS, Piech C, Portelance E, Potts C, Raghunathan A, Reich R, Ren H, Rong F, Roohani Y, Ruiz C, Ryan J, R\u00e9 C, Sadigh, D, Sagawa, S, Santhanam, K, Shih, A, Srinivasan, K, Tamkin, A, Taori, R, Thomas AW, Tram\u00e8r F, Wang RE, Wang W, Wu B, Wu J, Wu Y, Xie SM, Yasunaga M, You J, Zaharia M, Zhang M, Zhang T, Zhang X, Zhang Y, Zheng L, Zhou K, Liang P. On the Opportunities and Risks of Foundation Models 2022. arxiv:org\/abs\/2108.07258."},{"key":"4497_CR7","unstructured":"Saroufim M, Perlitz Y, Choshen L, Antiga L, Bowyer G, Puhrsch C, Guessous D, Rao S, Chauhan G, Kumar A, Kumar JP, Parikh RA, Isaacson J, Yang W. NeurIPS 2023 LLM Efficiency Fine-tuning Competition 2025. arxiv:org\/abs\/2503.13507"},{"key":"4497_CR8","unstructured":"Guo Y, Xu Z, Yang Y. Is chatgpt a financial expert? Evaluating language models on financial natural language processing"},{"key":"4497_CR9","doi-asserted-by":"publisher","unstructured":"Divate M, Jadhav P, Jha A, Joshi S, Dara K. Harnessing llms for financial forecasting: A systematic review of advances in stock market prediction and portfolio optimization 2024;12. https:\/\/doi.org\/10.22214\/ijraset.2024.65283.","DOI":"10.22214\/ijraset.2024.65283"},{"key":"4497_CR10","doi-asserted-by":"publisher","unstructured":"Xu T, MacDonald M: Financial sector and economic growth in india. IMF Working Papers 2022;2022,(1). https:\/\/doi.org\/10.5089\/9798400216404.001.","DOI":"10.5089\/9798400216404.001"},{"key":"4497_CR11","unstructured":"Islam P, Kannappan A, Kiela D, Qian R, Scherrer N, Vidgen B. FinanceBench: A New Benchmark for Financial Question Answering 2023. arxiv:org\/abs\/2311.11944."},{"key":"4497_CR12","doi-asserted-by":"crossref","unstructured":"Xie Q, Han W, Chen Z, Xiang R, Zhang X, He Y, et al. Finben: A holistic financial benchmark for large language models. Advances in Neural Information Processing Systems. 2025;37:95716\u201343.","DOI":"10.52202\/079017-3033"},{"key":"4497_CR13","unstructured":"Lu G, Guo X, Zhang R, Zhu W, Liu J. BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs 2025. arxiv:org\/abs\/2505.19457."},{"key":"4497_CR14","unstructured":"Li H, Cao Y, Yu Y, Javaji SR, Deng Z, He Y, Jiang Y, Zhu Z, Subbalakshmi K, Xiong G, Huang J, Qian L, Peng X, Xie Q, Suchow JW. INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent 2024. arxiv:org\/abs\/2412.18174."},{"key":"4497_CR15","doi-asserted-by":"crossref","unstructured":"Tang Y, Yang Y. FinMTEB: Finance Massive Text Embedding Benchmark 2025. arxiv:org\/abs\/2502.10990.","DOI":"10.18653\/v1\/2025.emnlp-main.179"},{"key":"4497_CR16","doi-asserted-by":"crossref","unstructured":"Zhu J, Li J, Wen Y, Guo L. Benchmarking large language models on cflue \u2013 a chinese financial language understanding evaluation dataset 2024.","DOI":"10.18653\/v1\/2024.findings-acl.337"},{"key":"4497_CR17","unstructured":"Xie Q, Han W, Chen Z, Xiang R, Zhang X, He Y, Xiao M, Li D, Dai Y, Feng D, Xu Y, Kang H, Kuang Z, Yuan C, Yang K, Luo Z, Zhang T, Liu Z, Xiong G, Deng Z, Jiang Y, Yao Z, Li H, Yu Y, Hu G, Huang J, Liu X-Y, Lopez-Lira A, Wang B, Lai Y, Wang, H, Peng M, Ananiadou S, Huang J. FinBen: A Holistic Financial Benchmark for Large Language Models 2024. arxiv:org\/abs\/2402.12659."},{"key":"4497_CR18","doi-asserted-by":"crossref","unstructured":"Bhatia G, Nagoudi EMB, Cavusoglu H, Abdul-Mageed M. FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models (2024). arxiv:org\/abs\/2402.10986","DOI":"10.18653\/v1\/2024.findings-acl.774"},{"key":"4497_CR19","doi-asserted-by":"publisher","unstructured":"Matlin G, Okamoto M, Pardawala H, Yang Y, Chava S. Financial language model evaluation (FLaME). In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 22633\u201322679. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.1164 . https:\/\/aclanthology.org\/2025.findings-acl.1164\/","DOI":"10.18653\/v1\/2025.findings-acl.1164"},{"key":"4497_CR20","doi-asserted-by":"crossref","unstructured":"Gan Z, Lu Y, Zhang D, Li H, Liu C, Liu J, Liu J, Wu H, Fu C, Xu Z, Zhang R, Dai, Y. MME-Finance: a Multimodal Finance Benchmark for Expert-level Understanding and Reasoning (2024). arxiv:org\/abs\/2411.03314","DOI":"10.1145\/3746027.3758230"},{"key":"4497_CR21","unstructured":"Li J, Zhu Y, Cheng D, Ding Z, Jiang C. CFBenchmark-MM: Chinese financial assistant benchmark for multimodal large language model (2025). arxiv:org\/abs\/2506.13055"},{"key":"4497_CR22","unstructured":"Kamble K, Russak M, Mozolevskyi D, Ali M, Russak M, AlShikh W. Expect the Unexpected: FailSafe long context QA for finance (2025). arxiv:org\/abs\/2502.06329"},{"key":"4497_CR23","doi-asserted-by":"publisher","unstructured":"Zhang Z, Cao Y, Liao L. XFinBench: Benchmarking LLMs in complex financial problem solving and reasoning. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the association for computational linguistics: ACL 2025, pp. 8715\u20138758. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.457 . https:\/\/aclanthology.org\/2025.findings-acl.457\/","DOI":"10.18653\/v1\/2025.findings-acl.457"},{"key":"4497_CR24","unstructured":"Yang X, Sun K, Xin H, Sun Y, Bhalla N, Chen X, Choudhary S, Gui RD, Jiang ZW, Jiang Z, Kong L, Moran B, Wang J, Xu Y.E, Yan A, Yang C, Yuan E, Zha H, Tang N, Chen L, Scheffer N, Liu Y, Shah N, Wanga R, Kumar A, Yih W-t, Dong XL, Labs MR. Crag-comprehensive rag benchmark"},{"key":"4497_CR25","unstructured":"Liu S, Zhao S, Jia C, Zhuang X, Long Z, Zhou J, Zhou A, Lan M, Chong Y. FinDABench: Benchmarking financial data analysis ability of large language models. In: Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B.D., Schockaert, S. (eds.) Proceedings of the 31st International Conference on Computational Linguistics, pp. 710\u2013725. Association for Computational Linguistics, Abu Dhabi, UAE (2025). https:\/\/aclanthology.org\/2025.coling-main.48\/"},{"key":"4497_CR26","doi-asserted-by":"crossref","unstructured":"Zhu J, Li J, Wen Y, Guo L. Benchmarking Large Language Models on CFLUE\u2014A Chinese Financial Language Understanding Evaluation Dataset (2024). arxiv:org\/abs\/2405.10542","DOI":"10.18653\/v1\/2024.findings-acl.337"},{"key":"4497_CR27","doi-asserted-by":"publisher","unstructured":"Chen Z, Chen W, Smiley C, Shah S, Borova I, Langdon D, Moussa R, Beane M, Huang TH, Routledge, B, Wang, WY. Finqa: A dataset of numerical reasoning over financial data. EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings, 3697\u20133711 (2021) https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.300","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"4497_CR28","unstructured":"Guo X, Xia H, Liu Z, Cao H, Yang Z, Liu Z, Wang S, Niu J, Wang C, Wang Y, Liang X, Huang X, Zhu B, Wei Z, Chen Y, Shen W, Zhang L. FinEval: a Chinese financial domain knowledge evaluation benchmark for large language models (2024). arxiv:org\/abs\/2308.09975"},{"key":"4497_CR29","doi-asserted-by":"publisher","unstructured":"Chen Z, Li S, Smiley C, Ma Z, Shah S, Wang WY. ConvFinQA: Exploring the chain of numerical reasoning in conversational finance question answering. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 conference on empirical methods in natural language processing, pp. 6279\u20136292. Association for computational linguistics, Abu Dhabi, United Arab Emirates (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.421. https:\/\/aclanthology.org\/2022.emnlp-main.421\/","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"4497_CR30","doi-asserted-by":"publisher","unstructured":"Shah R, Chawla K, Eidnani D, Shah A, Du W, Chava S, Raman N, Smiley C, Chen J, Yang D. When FLUE meets FLANG: Benchmarks and large pretrained language model for financial domain. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) 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). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.148. https:\/\/aclanthology.org\/2022.emnlp-main.148\/","DOI":"10.18653\/v1\/2022.emnlp-main.148"},{"key":"4497_CR31","doi-asserted-by":"publisher","unstructured":"Maia M, Handschuh S, Freitas A, Davis B, Mcdermott R, Zarrouk M, Balahur A, Mc-Dermott R. Www\u201918 open challenge, 1941\u20131942 (2018) https:\/\/doi.org\/10.1145\/3184558.3192301","DOI":"10.1145\/3184558.3192301"},{"key":"4497_CR32","unstructured":"Sprague Z, Yin F, Rodriguez J.D, Jiang D, Wadhwa M, Singhal P, Zhao X, Ye X, Mahowald K, Durrett G. To cot or not to cot? chain-of-thought helps mainly on math and symbolic reasoning. 13th International Conference on Learning Representations, ICLR 2025, 91018\u201391062 (2025)."},{"key":"4497_CR33","unstructured":"Zhu J, Li J, Wen Y, Guo L. Benchmarking large language models on cflue-a chinese financial language understanding evaluation dataset"},{"key":"4497_CR34","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1504\/IJICBM.2010.034389","volume":"3","author":"RK Agrawal","year":"2010","unstructured":"Agrawal RK, Majupuria A. An examination of role stress in chartered accountants in India. Int J Indian Culture Business Manag. 2010;3:577. https:\/\/doi.org\/10.1504\/IJICBM.2010.034389.","journal-title":"Int J Indian Culture Business Manag"},{"key":"4497_CR35","doi-asserted-by":"publisher","unstructured":"Li L, Sleem L, Gentile N, Nichil G, State R. Exploring the impact of temperature on large language models: Hot or cold? Procedia Computer Science 264, 242\u2013251 (2025). https:\/\/doi.org\/10.1016\/j.procs.2025.07.135.","DOI":"10.1016\/j.procs.2025.07.135"},{"key":"4497_CR36","doi-asserted-by":"publisher","unstructured":"Fazlija B, Ibraimi M, Forouzandeh A, Fazlija A. Implementing financial regulations using large language models. 2024. https:\/\/doi.org\/10.2139\/SSRN.5010694.","DOI":"10.2139\/SSRN.5010694"},{"key":"4497_CR37","unstructured":"Peeperkorn M, Kouwenhoven T, Brown D, Jordanous A. Is temperature the creativity parameter of large language models? (2024)"},{"key":"4497_CR38","doi-asserted-by":"crossref","unstructured":"Gupta J, Sharma A, Singhania S, Abidi AI. Legal assist ai: leveraging transformer-based model for effective legal assistance (2025) arXiv:2505.22003 [cs.CL]","DOI":"10.21203\/rs.3.rs-5351879\/v1"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04497-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04497-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04497-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:39:00Z","timestamp":1762843140000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04497-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":38,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["4497"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04497-x","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no financial or non-financial interests that are directly or indirectly related to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"All authors have approved the manuscript and consent to its publication.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"957"}}