{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:45:08Z","timestamp":1783140308109,"version":"3.54.6"},"reference-count":43,"publisher":"American Association for the Advancement of Science (AAAS)","funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62272379, T2341003, 62102310"],"award-info":[{"award-number":["No. 62272379, T2341003, 62102310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Natural Science Basic Research Program of Shaanxi Province","award":["2025JC-JCQN-081"],"award-info":[{"award-number":["2025JC-JCQN-081"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["xzy012023068"],"award-info":[{"award-number":["xzy012023068"]}]},{"name":"the XJTU Research Fund for Al Science","award":["2025YXYC004"],"award-info":[{"award-number":["2025YXYC004"]}]}],"content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:p>Financial reporting fraud poses a considerable threat to financial market stability. Traditional detection methods predominantly rely on quantitative data analysis while neglecting the informational value of textual disclosures, and existing text analysis approaches suffer from 3 critical limitations: inadequate interpretability, poor domain adaptability, and absence of temporal continuity modeling. This paper proposes the financial statement fraud detection large language model (FSFDLLM) framework, which leverages large language models (LLMs) to achieve in-depth textual feature extraction and interpretable reasoning. Our methodology addresses 3 key challenges: (a) Specifically, we develop a structured prompting mechanism to guide the LLM in conducting the fraud risk assessment of financial texts while generating explanatory rationales. (b) We construct a hybrid learning architecture that integrates LLM-generated pseudo-labels and rationale chains as enhanced features with structured financial data for joint classification model training. (c) The framework has 3 distinctive features: First, it overcomes the domain transfer bottleneck in conventional natural language processing (NLP) models by harnessing the LLM\u2019s semantic comprehension to accurately capture domain-specific financial terminology. Second, it establishes an auditable decision evidence chain through LLM-generated explanatory rationales, thereby enhancing regulatory compliance. Third, it captures continuous fraud patterns by modeling temporal financial indicators and inter-period textual semantic correlations. Experimental evaluations on a real-world listed company dataset demonstrate that our framework considerably outperforms baseline models in key metrics including F1-score and area under the receiver operating characteristic curve (AUC), while the generated explanatory text provides verifiable semantic evidence for regulatory scrutiny. This study presents a cross-modal solution for financial statement fraud detection (FSFD) that harmonizes high accuracy with interpretability, offering practical value for enhancing financial regulatory technology tools.<\/jats:p>","DOI":"10.34133\/icomputing.0274","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:31:20Z","timestamp":1775028680000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["FSFDLLM: Financial Statement Fraud Detection Aided by Large Language Models"],"prefix":"10.34133","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5624-8254","authenticated-orcid":true,"given":"Yumeng","family":"Dai","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi 710049, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyu","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi 710049, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoguang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi 710049, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, \rGriffith University, Brisbane, Australia."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9539-5046","authenticated-orcid":true,"given":"Chenxu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi 710049, China."},{"name":"MoE Key Lab of Intelligent Networks and Network Security (INNS), Xi\u2019an Jiaotong University, Xi\u2019an","place":["China"]},{"name":"Interdisciplinary Research Center of Frontier Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an","place":["China"]},{"name":"Shaanxi Joint (Key) Laboratory for Artificial Intelligence, Xi\u2019an Jiaotong University, Xi\u2019an","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"issue":"3","key":"e_1_3_3_2_2","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/S1045-2354(03)00072-8","article-title":"Causes, consequences, and deterence of financial statement fraud","volume":"16","author":"Rezaee Z","year":"2005","unstructured":"Rezaee Z. Causes, consequences, and deterence of financial statement fraud. Critic Perspect Account. 2005;16(3):277\u2013298.","journal-title":"Critic Perspect Account."},{"issue":"2","key":"e_1_3_3_3_2","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.orgdyn.2007.03.002","article-title":"Understanding the causes and effects of top management fraud","volume":"36","author":"Zahra SA","year":"2007","unstructured":"Zahra SA, Priem RL, Rasheed AA. Understanding the causes and effects of top management fraud. Organ Dyn. 2007;36(2):122\u2013139.","journal-title":"Organ Dyn."},{"key":"e_1_3_3_4_2","unstructured":"Lumpkin SA. Regulatory issues related to financial innovation. Paris (France); OECD; 2010."},{"key":"e_1_3_3_5_2","first-page":"421","article-title":"Financial statement fraud: A review from the era surrounding the financial crisis","volume":"13","author":"Grandstaff JL","year":"2021","unstructured":"Grandstaff JL, Solsma LL. Financial statement fraud: A review from the era surrounding the financial crisis. J Forensic Invest Account. 2021;13:421\u2013437.","journal-title":"J Forensic Invest Account."},{"key":"e_1_3_3_6_2","unstructured":"Koroteev MV. BERT: A review of applications in natural language processing and understanding. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.11943"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1017\/S1351324916000334","article-title":"Word2Vec","volume":"23","author":"Church KW","year":"2017","unstructured":"Church KW. Word2Vec. Nat Lang Eng. 2017;23:155\u2013162.","journal-title":"Nat Lang Eng."},{"issue":"2","key":"e_1_3_3_8_2","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.1111\/acfi.13390","article-title":"Accounting fraud detection through textual risk disclosures in annual reports: From the perspective of SEC guidelines","volume":"65","author":"Zhu X","year":"2025","unstructured":"Zhu X, Wu H, Chang Y, Li J. Accounting fraud detection through textual risk disclosures in annual reports: From the perspective of SEC guidelines. Account Finance. 2025;65(2):1837\u20131862.","journal-title":"Account Finance."},{"issue":"2","key":"e_1_3_3_9_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.hcc.2024.100211","article-title":"A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly","volume":"4","author":"Yao Y","year":"2024","unstructured":"Yao Y, Duan J, Xu K, Cai Y, Sun Z, Zhang Y. A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly. High-Confidence Comput. 2024;4(2): Article 100211.","journal-title":"High-Confidence Comput."},{"issue":"1","key":"e_1_3_3_10_2","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1111\/auar.12079","article-title":"Business continuity in the face of fraud and organisational change","volume":"26","author":"Margret J","year":"2016","unstructured":"Margret J, Hoque Z. Business continuity in the face of fraud and organisational change. Austral Account Rev. 2016;26(1):21\u201333.","journal-title":"Austral Account Rev."},{"issue":"3","key":"e_1_3_3_11_2","doi-asserted-by":"crossref","first-page":"38","DOI":"10.19030\/jabr.v11i3.5858","article-title":"Using financial statement data to identify factors associated with fraudulent financial reporting","volume":"11","author":"Persons OS","year":"1995","unstructured":"Persons OS. Using financial statement data to identify factors associated with fraudulent financial reporting. J Appl Bus Res. 1995;11(3):38\u201346.","journal-title":"J Appl Bus Res."},{"key":"e_1_3_3_12_2","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.knosys.2015.08.011","article-title":"Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts\u2019 judgments","volume":"89","author":"Lin CC","year":"2015","unstructured":"Lin CC, Chiu AA, Huang SY, Yen DC. Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts\u2019 judgments. Knowl Based Syst. 2015;89:459\u2013470.","journal-title":"Knowl Based Syst."},{"issue":"1","key":"e_1_3_3_13_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.2308\/jeta.2010.7.1.25","article-title":"Can linguistic predictors detect fraudulent financial filings?","volume":"7","author":"Goel S","year":"2010","unstructured":"Goel S, Gangolly J, Faerman SR, Uzuner O. Can linguistic predictors detect fraudulent financial filings? J Emerg Technol Account. 2010;7(1):25\u201346.","journal-title":"J Emerg Technol Account"},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Li S Zou C Li Y Zhao X Gao Y. Attention-based multi-modal fusion network for semantic scene completion. In: Proceedings of the AAAI Conference on Artificial Intelligence. New York (NY): AAAI; 2020. p. 11402\u201311409.","DOI":"10.1609\/aaai.v34i07.6803"},{"issue":"2","key":"e_1_3_3_15_2","first-page":"75","article-title":"Beyond the numbers: Mining the annual reports for hidden cues indicative of financial statement fraud","volume":"19","author":"Goel S","year":"2012","unstructured":"Goel S, Gangolly J. Beyond the numbers: Mining the annual reports for hidden cues indicative of financial statement fraud. Intell Syst Account Finance Manage. 2012;19(2):75\u201389.","journal-title":"Intell Syst Account Finance Manage."},{"issue":"1","key":"e_1_3_3_16_2","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.dss.2010.07.012","article-title":"Making words work: Using financial text as a predictor of financial events","volume":"50","author":"Cecchini M","year":"2010","unstructured":"Cecchini M, Aytug H, Koehler GJ, Pathak P. Making words work: Using financial text as a predictor of financial events. Decis Support Syst. 2010;50(1):164\u2013175.","journal-title":"Decis Support Syst."},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.dss.2020.113421","article-title":"Deep learning for detecting financial statement fraud","volume":"139","author":"Craja P","year":"2020","unstructured":"Craja P, Kim A, Lessmann S. Deep learning for detecting financial statement fraud. Decis Support Syst. 2020;139: Article 113421.","journal-title":"Decis Support Syst."},{"key":"e_1_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Mastropaolo A Scalabrino S Cooper N Palacio DN Poshyvannyk D Oliveto R Bavota G. Studying the usage of text-to-text transfer transformer to support code-related tasks. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). New York (NY): IEEE; 2021. p. 336\u2013347.","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_3_19_2","unstructured":"Li Z Zhang X Zhang Y Long D Xie P Zhang M. Towards general text embeddings with multi-stage contrastive learning. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2308.03281"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.eng.2022.04.024","article-title":"Pre-trained language models and their applications","volume":"25","author":"Wang H","year":"2023","unstructured":"Wang H, Li J, Wu H, Hovy E, Sun Y. Pre-trained language models and their applications. Engineering. 2023;25:51\u201365.","journal-title":"Engineering"},{"key":"e_1_3_3_21_2","unstructured":"Achiam J Adler S Agarwal S Ahmad L Akkaya I Aleman FL Almeida D Altenschimdt J Altman S Anadkat S et\u00a0al. GPT-4 technical report. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.08774"},{"key":"e_1_3_3_22_2","unstructured":"Anil R Dai AM Firat O Johnson M Lepikhin D Passos A Shakeri S Taropa E Bailey P Chen Z et\u00a0al. Palm 2 technical report. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.10403"},{"key":"e_1_3_3_23_2","unstructured":"Dubey A Jauhri A Pandey A Kadlan A Al-Dahle A Letman A Mathur A Schelten A Vaughan A Yang A et\u00a0al. The Llama 3 herd of models. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2407.21783"},{"key":"e_1_3_3_24_2","unstructured":"Team G Georgiev P Lei VI Burnell R Bai L Gulati A Tanzer G Vincent D Pan Z Wang S et\u00a0al. Gemini 1.5: Unlocking multimodal understanding across mil lions of tokens of context. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2403.05530"},{"key":"e_1_3_3_25_2","unstructured":"Team GLM Zeng A Xu B Wang B Zhang C Yin D Zhang D Rojas D Feng G Zhao H et\u00a0al. ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2406.12793"},{"key":"e_1_3_3_26_2","unstructured":"Wu S Irsoy O Lu S Dabravolski V Dredze M Gehrmann S Kambadur P Rosenberg D Mann G. BloombergGPT: A large language model for finance. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.17564"},{"key":"e_1_3_3_27_2","unstructured":"Lee J Stevens N Han SC Song M. A survey of large language models in finance (FinLLMs). arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2402.02315"},{"key":"e_1_3_3_28_2","unstructured":"Nie Y Kong Y Dong X Mulvey JM Poor V Wen Q Zohren S. A survey of large language models for financial applications: Progress prospects and challenges. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2406.11903"},{"key":"e_1_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Li Y Wang S Ding H Chen H. Large language models in finance: A survey. In: Proceedings of the Fourth ACM International Conference on AI in Finance. New York (NY): ACM; 2023. p. 374\u2013382.","DOI":"10.1145\/3604237.3626869"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Zhang J Bui T Yoon S Chen X Liu Z Xia C Tran QH Chang W Yu P. Few-shot intent detection via contrastive pre-training and fine tuning. arXiv. 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.144","DOI":"10.18653\/v1\/2021.emnlp-main.144"},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Wang X Wang C Liu H Wang M Qin T Wang P. FiGraph: A dynamic heterogeneous graph dataset for financial anomaly detection. In: Companion Proceedings of the ACM on Web Conference 2025. Sydney (Australia); ACM; 2025. p. 813\u2013816.","DOI":"10.1145\/3701716.3715301"},{"key":"e_1_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Taud H Mas JF. Multilayer perceptron (MLP). In: Geomatic approaches for modeling land change scenarios. Berlin (Germany): Springer; 2017. p. 451\u2013455.","DOI":"10.1007\/978-3-319-60801-3_27"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Zhao Y Hryniewicki MK. XGBOD: Improving supervised outlier detection with unsupervised representation learning. In: 2018 International Joint Conference on Neural Networks (IJCNN). New York (NY): IEEE; 2018. p. 1\u20138.","DOI":"10.1109\/IJCNN.2018.8489605"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Seiffert C Khoshgoftaar TM Van Hulse J Napolitano A. RUSBoost: A hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern A Syst Hum. 2009;40(1):185\u2013197.","DOI":"10.1109\/TSMCA.2009.2029559"},{"key":"e_1_3_3_35_2","volume-title":"XGBoost: A scalable tree boosting system","author":"Chen T.","year":"2016","unstructured":"Chen T. XGBoost: A scalable tree boosting system. New York (NY): Cornell University; 2016."},{"key":"e_1_3_3_36_2","unstructured":"Ke G Meng Q Finley T Wang T Chen W Ma W Ye Q Liu TY LightGBM: A highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems. Long Beach (CA): Curran Associates Inc.; 2017."},{"key":"e_1_3_3_37_2","unstructured":"Prokhorenkova L Gusev G Vorobev A Dorogush AV Gulin A. CatBoost: Unbiased boosting with categorical features. In: Advances in Neural Information Processing Systems. Montreal (Canada): Curran Associates Inc.; 2018."},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Arik SO Pfister T. Tabnet: Attentive interpretable tabular learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. Burlingame (CA): AAAI; 2021.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"e_1_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Dai H Wu S Huang J Jian Z Zhu Y Hu H Chen Z. FT-Transformer: Resilient and reliable transformer with end to-end fault tolerant attention. In: Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis. New York (NY): ACM; 2025. p. 1085\u20131098.","DOI":"10.1145\/3712285.3759853"},{"key":"e_1_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Liu XY Wang G Yang H Zha D. FinGPT: Democratizing internet-scale data for financial large language models. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2307.10485","DOI":"10.2139\/ssrn.4489826"},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Wang Y Zhang J Huang Z Li W Feng S Ma Z Sun Y Yu D Dong F Jin J et\u00a0al. Label information enhanced fraud detection against low homophily in graphs. In: Proceedings of the ACM Web Conference 2023. Austin (TX): ACM; 2023. p. 406\u2013416.","DOI":"10.1145\/3543507.3583373"},{"key":"e_1_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Xiang S Zhu M Cheng D Li E Zhao R Ouyang Y Chen L Zheng Y. Semi-supervised credit card fraud detection via attribute driven graph representation. In: Proceedings of the AAAI Conference on Artificial Intelligence. Washington (DC): AAAI; 2023.","DOI":"10.1609\/aaai.v37i12.26702"},{"key":"e_1_3_3_43_2","unstructured":"Opitz J Burst S. Macro F1 and macro F1. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1911.03347"},{"key":"e_1_3_3_44_2","unstructured":"Grandini M Bagli E Visani G. Metrics for multi-class classification: An overview. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2008.05756"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:01:31Z","timestamp":1777449691000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":43,"alternative-id":["10.34133\/icomputing.0274"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0274","relation":{},"ISSN":["2771-5892"],"issn-type":[{"value":"2771-5892","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"assertion":[{"value":"2025-08-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-24","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0274"}}