{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T10:29:46Z","timestamp":1771324186993,"version":"3.50.1"},"reference-count":57,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":46,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72301217"],"award-info":[{"award-number":["72301217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2024NSFSC1055"],"award-info":[{"award-number":["2024NSFSC1055"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Risk disclosures play a crucial role in the investment decision\u2010making processes for investors. However, extracting relevant variables from unstructured financial text poses a nontrivial challenge. In this paper, we propose RiskBERT, a large language model (LLM) trained on financial texts and risk knowledge graphs, specifically designed for risk factors extraction. By incorporating both finance and risk knowledge, RiskBERT significantly improves the extraction of risk factors in financial texts. We evaluate RiskBERT\u2019s performance on a labeled risk factors dataset comprising 119,153 sentences from 2400 Chinese A\u2010listed companies and compare it against other LLMs and automated text analysis algorithms for risk types\u2019 classification. Our findings demonstrate that RiskBERT outperforms alternative models, particularly when the training sample size is limited. Moreover, we uncover that RiskBERT provides risk informativeness estimates in annual reports that are at least 4.5% higher than those derived from other models. These results highlight the value of RiskBERT as a powerful tool for extracting risk factors and enhancing risk analysis in finance and accounting domains.<\/jats:p>","DOI":"10.1155\/int\/9295056","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T10:46:01Z","timestamp":1771238761000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Risk Factor Extraction in Financial Disclosures via a Knowledge Graph\u2013Enhanced Language Model"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1611-7206","authenticated-orcid":false,"given":"Yangcheng","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5995-5270","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-3896","authenticated-orcid":false,"given":"Dapeng","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9220-8647","authenticated-orcid":false,"given":"Gang","family":"Kou","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"e_1_2_14_1_2","first-page":"143","article-title":"Textual Analysis of Corporate Disclosures: A Survey of the Literature","volume":"29","author":"Li F.","year":"2010","journal-title":"Journal of Accounting Literature"},{"key":"e_1_2_14_2_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2014.1930"},{"key":"e_1_2_14_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-013-9258-3"},{"key":"e_1_2_14_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-016-9371-1"},{"key":"e_1_2_14_5_2","doi-asserted-by":"publisher","DOI":"10.1111\/1911-3846.12832"},{"key":"e_1_2_14_6_2","doi-asserted-by":"publisher","DOI":"10.2308\/HORIZONS-19-161"},{"key":"e_1_2_14_7_2","article-title":"Pre-Training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin J.","year":"2018","journal-title":"arXiv:1810.04805 [cs]"},{"key":"e_1_2_14_8_2","volume-title":"Language Models Are Unsupervised Multitask Learners","author":"Radford A.","year":"2019"},{"key":"e_1_2_14_9_2","doi-asserted-by":"crossref","unstructured":"LiuY. ChengH. KlopferR. GormleyM. R. andSchaafT. Effective Convolutional Attention Network for Multi-label Clinical Document Classification Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2021 Association for Computational Linguistics Online and Punta Cana Dominican Republic 5941\u20135953 https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.481.","DOI":"10.18653\/v1\/2021.emnlp-main.481"},{"key":"e_1_2_14_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21286"},{"key":"e_1_2_14_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"e_1_2_14_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110173"},{"key":"e_1_2_14_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/1911-3846.12825"},{"key":"e_1_2_14_14_2","doi-asserted-by":"publisher","DOI":"10.1111\/1475-679X.12123"},{"key":"e_1_2_14_15_2","doi-asserted-by":"publisher","DOI":"10.2308\/accr-52507"},{"key":"e_1_2_14_16_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4156"},{"key":"e_1_2_14_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacceco.2016.09.001"},{"key":"e_1_2_14_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-019-09507-x"},{"key":"e_1_2_14_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-021-09655-z"},{"key":"e_1_2_14_20_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-679X.2010.00396.x"},{"key":"e_1_2_14_21_2","doi-asserted-by":"publisher","DOI":"10.1111\/1911-3846.12414"},{"key":"e_1_2_14_22_2","doi-asserted-by":"publisher","DOI":"10.1177\/0021943608319388"},{"key":"e_1_2_14_23_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2010.01625.x"},{"key":"e_1_2_14_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.irfa.2014.02.006"},{"key":"e_1_2_14_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcorpfin.2017.05.017"},{"key":"e_1_2_14_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-020-03520-z"},{"key":"e_1_2_14_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-020-09575-4"},{"key":"e_1_2_14_28_2","doi-asserted-by":"publisher","DOI":"10.2308\/accr-51562"},{"key":"e_1_2_14_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-020-09563-8"},{"key":"e_1_2_14_30_2","doi-asserted-by":"crossref","unstructured":"BrownS. V. HinsonL. A. andTuckerJ. W. Financial Statement Adequacy and Firms 2023 MD&A Disclosures. Work paperhttps:\/\/doi.org\/10.2139\/ssrn.3891572.","DOI":"10.2139\/ssrn.3891572"},{"key":"e_1_2_14_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-020-09546-9"},{"key":"e_1_2_14_32_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-679X.2010.00382.x"},{"key":"e_1_2_14_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacceco.2017.07.002"},{"key":"e_1_2_14_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacceco.2016.07.003"},{"key":"e_1_2_14_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.irfa.2019.05.006"},{"key":"e_1_2_14_36_2","unstructured":"MikolovT. SutskeverI. ChenK. CorradoG. andDeanJ. Distributed Representations of Words and Phrases and Their Compositionality arXiv:1310.4546."},{"key":"e_1_2_14_37_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"e_1_2_14_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2013.01.007"},{"key":"e_1_2_14_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pacfin.2020.101322"},{"key":"e_1_2_14_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2011.05.011"},{"key":"e_1_2_14_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacceco.2015.09.002"},{"key":"e_1_2_14_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfs.2016.12.004"},{"key":"e_1_2_14_43_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2009.01543.x"},{"key":"e_1_2_14_44_2","doi-asserted-by":"publisher","DOI":"10.1111\/jfir.12141"},{"key":"e_1_2_14_45_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2006.00895.x"},{"key":"e_1_2_14_46_2","unstructured":"SunZ. DengZ.-H. NieJ.-Y. andTangJ. R.E. Knowledge Graph Embedding by Relational Rotation in Complex Space International Conference on Learning Representations 2018."},{"key":"e_1_2_14_47_2","article-title":"Gaussian Error Linear Units (GELUs)","author":"Hendrycks D.","year":"2018","journal-title":"arXiv:1606.08415"},{"key":"e_1_2_14_48_2","unstructured":"CuiY. Pre-Training With Whole Word Masking for Chinese BERT arXiv:1906.08101."},{"key":"e_1_2_14_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2019618.2019624"},{"key":"e_1_2_14_50_2","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Liu Y.","year":"2019","journal-title":"arXiv:1907.11692 [cs]"},{"key":"e_1_2_14_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"e_1_2_14_52_2","doi-asserted-by":"crossref","unstructured":"XuanX. WenF. ChuB.et al. Finbert2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-specific Deployment of Large Language Models Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD\u201925) 2025 5117\u20135128 https:\/\/doi.org\/10.1145\/3711896.3737219.","DOI":"10.1145\/3711896.3737219"},{"key":"e_1_2_14_53_2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.1270974"},{"key":"e_1_2_14_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-014-9278-7"},{"key":"e_1_2_14_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11142-017-9414-2"},{"key":"e_1_2_14_56_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1027351630866"},{"key":"e_1_2_14_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-4101(01)00030-1"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9295056","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/9295056","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9295056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T09:34:28Z","timestamp":1771320868000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/9295056"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/9295056"],"URL":"https:\/\/doi.org\/10.1155\/int\/9295056","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9295056"}}