IDEAS home Printed from https://ideas.repec.org/a/eee/ijoais/v56y2025ics1467089525000260.html

Discriminative meets generative: Automated information retrieval from unstructured corporate documents via (large) language models

Author

Listed:
  • Levich, Sergej
  • Knust, Lucas

Abstract

This paper demonstrates the potential of (large) language models to transform accounting practice and research by automating information retrieval from unstructured sources. While information retrieval in accounting has hitherto been predominantly addressed through handcrafted, rule-based systems, we have devised an approach based entirely on machine learning methods from the field of natural language processing (NLP). Specifically, we consider and contrast two modeling paradigms in NLP: discriminative modeling and generative modeling. In the former case, we fine-tune a language model pre-trained for multilingual, visually rich document understanding. In the latter, we apply prompting techniques to utilize a large language model (LLM) without prior training. We illustrate our approach by retrieving group ownership data from annual reports in Portable Document Format (PDF). We successfully retrieve group ownership information for both modeling paradigms, achieving a strong overall accuracy with a low percentage of false negatives. Furthermore, we consider the impact of different reporting languages and accounting standards.

Suggested Citation

  • Levich, Sergej & Knust, Lucas, 2025. "Discriminative meets generative: Automated information retrieval from unstructured corporate documents via (large) language models," International Journal of Accounting Information Systems, Elsevier, vol. 56(C).
    • Handle: RePEc:eee:ijoais:v:56:y:2025:i:c:s1467089525000260
    DOI: 10.1016/j.accinf.2025.100750
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1467089525000260
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.accinf.2025.100750?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Christof Beuselinck & Stefano Cascino & Marc Deloof & Ann Vanstraelen, 2019. "Earnings management within multinational corporations," Post-Print hal-01914626, HAL.
    2. Mahmoud El‐Haj & Paul Rayson & Martin Walker & Steven Young & Vasiliki Simaki, 2019. "In search of meaning: Lessons, resources and next steps for computational analysis of financial discourse," Journal of Business Finance & Accounting, Wiley Blackwell, vol. 46(3-4), pages 265-306, March.
    3. Elizabeth Blankespoor & Brian P. Miller & Hal D. White, 2014. "Initial evidence on the market impact of the XBRL mandate," Review of Accounting Studies, Springer, vol. 19(4), pages 1468-1503, December.
    4. Duan, Huijue Kelly & Vasarhelyi, Miklos A. & Codesso, Mauricio & Alzamil, Zamil, 2023. "Enhancing the government accounting information systems using social media information: An application of text mining and machine learning," International Journal of Accounting Information Systems, Elsevier, vol. 48(C).
    5. Amitav Saha & Richard D. Morris & Helen Kang, 2019. "Disclosure Overload? An Empirical Analysis of International Financial Reporting Standards Disclosure Requirements," Abacus, Accounting Foundation, University of Sydney, vol. 55(1), pages 205-236, March.
    6. Markus Widmann & Florian Follert & Matthias Wolz, 2021. "What is it going to cost? Empirical evidence from a systematic literature review of audit fee determinants," Management Review Quarterly, Springer, vol. 71(2), pages 455-489, April.
    7. Wil Aalst & Martin Bichler & Armin Heinzl, 2016. "Open Research in Business and Information Systems Engineering," Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK, Springer;Gesellschaft für Informatik e.V. (GI), vol. 58(6), pages 375-379, December.
    8. Blankespoor, Elizabeth & deHaan, Ed & Marinovic, Iván, 2020. "Disclosure processing costs, investors’ information choice, and equity market outcomes: A review," Journal of Accounting and Economics, Elsevier, vol. 70(2).
    9. Dong, Mengming Michael & Stratopoulos, Theophanis C. & Wang, Victor Xiaoqi, 2024. "A scoping review of ChatGPT research in accounting and finance," International Journal of Accounting Information Systems, Elsevier, vol. 55(C).
    10. Appelbaum, Deniz & Kogan, Alexander & Vasarhelyi, Miklos & Yan, Zhaokai, 2017. "Impact of business analytics and enterprise systems on managerial accounting," International Journal of Accounting Information Systems, Elsevier, vol. 25(C), pages 29-44.
    11. Joost Impink & Mari Paananen & Annelies Renders, 2022. "Regulation‐induced Disclosures: Evidence of Information Overload?," Abacus, Accounting Foundation, University of Sydney, vol. 58(3), pages 432-478, September.
    12. Vincent Tawiah & Hela Borgi, 2022. "Impact of XBRL adoption on financial reporting quality: a global evidence," Accounting Research Journal, Emerald Group Publishing Limited, vol. 35(6), pages 815-833, August.
    13. Justin Chircop & Monika Tarsalewska, 2020. "10-K Filing length and M&A returns," The European Journal of Finance, Taylor & Francis Journals, vol. 26(6), pages 532-553, April.
    14. Lang, Mark & Stice-Lawrence, Lorien, 2015. "Textual analysis and international financial reporting: Large sample evidence," Journal of Accounting and Economics, Elsevier, vol. 60(2), pages 110-135.
    15. Javier Cravino & Andrei A. Levchenko, 2017. "Multinational Firms and International Business Cycle Transmission," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 132(2), pages 921-962.
    16. Mahmoud El-Haj & Paulo Alves & Paul Rayson & Martin Walker & Steven Young, 2020. "Retrieving, classifying and analysing narrative commentary in unstructured (glossy) annual reports published as PDF files," Accounting and Business Research, Taylor & Francis Journals, vol. 50(1), pages 6-34, January.
    17. David Oesch & Felix Urban, 2022. "The effect of international subsidiaries on voluntary disclosure - evidence from natural disasters," Accounting and Business Research, Taylor & Francis Journals, vol. 52(3), pages 223-253, April.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Stratopoulos, Theophanis C. & Wang, Victor Xiaoqi, 2025. "Artificial intelligence and accounting research: a framework and agenda," International Journal of Accounting Information Systems, Elsevier, vol. 56(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Miles Gietzmann & Francesco Grossetti & Craig M. Lewis, 2026. "Investor distraction and multi-dimensional financial narrative," Review of Accounting Studies, Springer, vol. 31(1), pages 334-373, March.
    2. Olga Bogachek & Antonio De Vito & Paul Demeré & Francesco Grossetti, 2026. "Using narrative disclosures to predict tax outcomes," Review of Accounting Studies, Springer, vol. 31(1), pages 374-412, March.
    3. Cheng, Qiang & Lin, Pengkai & Zhao, Yue, 2025. "Does generative AI facilitate investor Trading? Early evidence from ChatGPT outages," Journal of Accounting and Economics, Elsevier, vol. 80(2).
    4. de Villiers, Charl & Dimes, Ruth & Molinari, Matteo, 2026. "The role of sustainability awards in institutionalising sustainability: Case study evidence," The British Accounting Review, Elsevier, vol. 58(1).
    5. Huanyu Ma & Xuegang Sun, 2025. "The impact of economic policy uncertainty on earnings value relevance," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 30(3), pages 2427-2449, July.
    6. Grommes, Alexander, 2025. "Impact of audit assurance on the quality of sustainability reporting," Junior Management Science (JUMS), Junior Management Science e. V., vol. 10(1), pages 201-235.
    7. Belnap, Andrew, 2023. "The effect of intermediary coverage on disclosure: Evidence from a randomized field experiment," Journal of Accounting and Economics, Elsevier, vol. 75(1).
    8. Eduardo Schiehll & Sam Kolahgar, 2021. "Financial materiality in the informativeness of sustainability reporting," Business Strategy and the Environment, Wiley Blackwell, vol. 30(2), pages 840-855, February.
    9. Dyer, Travis A. & Glaeser, Stephen & Lang, Mark H. & Sprecher, Caroline, 2024. "The effect of patent disclosure quality on innovation," Journal of Accounting and Economics, Elsevier, vol. 77(2).
    10. Aghamolla, Cyrus & Smith, Kevin, 2023. "Strategic complexity in disclosure," Journal of Accounting and Economics, Elsevier, vol. 76(2).
    11. Vicente Cuñat & Moqi Groen-Xu, 2025. "Timing Complex News to Target Attention," Management Science, INFORMS, vol. 71(9), pages 7774-7799, September.
    12. Khaldoon Albitar & Tony Abdoush & Khaled Hussainey, 2023. "Do corporate governance mechanisms and ESG disclosure drive CSR narrative tones?," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 28(4), pages 3876-3890, October.
    13. Danial Hemmings & Lynn Hodgkinson & Gwion Williams, 2020. "It's OK to pay well, if you write well: The effects of remuneration disclosure readability," Journal of Business Finance & Accounting, Wiley Blackwell, vol. 47(5-6), pages 547-586, May.
    14. Charles G. McClure & Shawn X. Shi & Edward M. Watts, 2025. "Information acquisition costs and price informativeness: global evidence," Review of Accounting Studies, Springer, vol. 30(3), pages 2468-2507, September.
    15. Jackie Zhanbiao Li & Saeed Awadh Bin-Nashwan & Yingqian Lao & Chai Lee Goi & Yew Hua Ling, 2025. "Unraveling the impact of social media on accounting information disclosure: does government supervision matter?," Humanities and Social Sciences Communications, Palgrave Macmillan, vol. 12(1), pages 1-16, December.
    16. Julian Junyan Wang & Victor Xiaoqi Wang, 2024. "Leveraging Large Language Models to Democratize Access to Costly Datasets for Academic Research," Papers 2412.02065, arXiv.org, revised Sep 2025.
    17. Bertomeu, Jeremy & Lin, Yupeng & Liu, Yibin & Ni, Zhenghui, 2025. "The impact of generative AI on information processing: Evidence from the ban of ChatGPT in Italy," Journal of Accounting and Economics, Elsevier, vol. 80(1).
    18. Chenghao Huang & Siyang Tian, 2026. "Actual share repurchases, private information, and stock price crash risk: Evidence from China’s reformed open market repurchase program," Review of Quantitative Finance and Accounting, Springer, vol. 66(2), pages 831-866, February.
    19. Amitav Saha & Sudipta Bose, 2021. "Do IFRS disclosure requirements reduce the cost of capital? Evidence from Australia," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 61(3), pages 4669-4701, September.
    20. S. M. R. K. Samarakoon & R. K. Mishra & Rudra P. Pradhan & Manju Jayakumar & Tapan P. Bagchi, 2025. "Annual report readability, ESG disclosure, and risk perspectives of Indian firms: the mediating role of corporate governance and earnings management," International Journal of Disclosure and Governance, Palgrave Macmillan, vol. 22(3), pages 678-705, September.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods
    • C81 - Mathematical and Quantitative Methods - - Data Collection and Data Estimation Methodology; Computer Programs - - - Methodology for Collecting, Estimating, and Organizing Microeconomic Data; Data Access
    • D80 - Microeconomics - - Information, Knowledge, and Uncertainty - - - General
    • M40 - Business Administration and Business Economics; Marketing; Accounting; Personnel Economics - - Accounting - - - General

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:ijoais:v:56:y:2025:i:c:s1467089525000260. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/international-journal-of-accounting-information-systems/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.