Evidence-Grounded Accounting Disclosure Review Cards: A Visual Communication Framework for LLM-Style Explanations over SEC Financial Statements and Notes
DOI:
https://doi.org/10.51903/ijgd.v3i2.3710Keywords:
LLM explanations, SEC filings, EDGAR, financial statement data, visual communication, UI/UX, citation trail, human-AI decision supportAbstract
This paper presents evidence-grounded accounting disclosure review cards, a visual communication framework for LLM-style explanations over SEC financial statements and notes. The revised study positions the card as an accounting evidence interface rather than as a test of real analyst performance or a live LLM pipeline. The objective is to organize structured statement facts, note-level disclosure evidence, ratio signals, citation trails, and review actions so that accounting claims can be inspected and challenged within a compact card. The evaluation combines the 2024 EDGAR quarterly master indexes, the 2024 SEC Financial Statement Data Sets, and the 2024 Q3-Q4 Financial Statement and Notes Data Sets. The master-index universe contains 1,241,395 filings, including 25,993 10-K/10-Q-family filings. The statement-level analysis uses 23,677 10-K/10-Q-family rows from 6,077 companies across 70 SIC groups, and 20,753 rows (87.65%) contain enough statement evidence to populate the core card. The statement-note paired analysis covers 11,880 filings from 5,811 companies, of which 10,391 (87.47%) are card-ready after note evidence is added. A stratified accounting review benchmark of 400 filings generates 2,400 evidence-checking tasks. The results support the feasibility of the proposed accounting evidence architecture and clarify that the reported outcomes describe data coverage, evidence readiness, and disclosure mapping rather than observed human speed, workload, trust, or live-model reliability.
References
Abdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018). Trends and trajectories for explainable, accountable and intelligible systems: An HCI research agenda. Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3173574.3174156
Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., Avila, R., Babuschkin, I., Balaji, S., Balcom, V., Berner, C., Brockman, G., ... Zoph, B. (2023). GPT-4 technical report. arXiv. https://doi.org/10.48550/arXiv.2303.08774
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610-623. https://doi.org/10.1145/3442188.3445922
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877-1901.
Cleveland, W. S., & McGill, R. (1984). Graphical perception: Theory, experimentation, and application to the development of graphical methods. Journal of the American Statistical Association, 79(387), 531-554. https://doi.org/10.1080/01621459.1984.10478080
Financial Accounting Standards Board. (2021). Concepts Statement No. 8: Conceptual framework for financial reporting, Chapter 1, The objective of general purpose financial reporting, as amended. FASB.
Financial Accounting Standards Board. (2024). Concepts Statement No. 8: Conceptual framework for financial reporting, Chapter 3, Qualitative characteristics of useful financial information, as amended. FASB.
Heer, J., Bostock, M., & Ogievetsky, V. (2010). A tour through the visualization zoo. Communications of the ACM, 53(6), 59-67. https://doi.org/10.1145/1743546.1743567
International Organization for Standardization. (2019). ISO 9241-210:2019: Ergonomics of human-system interaction-Part 210: Human-centred design for interactive systems. ISO.
Jason Kuhn, Yushan Chen, & Evelyn Chan. (2024). AI-Driven Mobile UI Pattern Recognition and Design Topic Mining on RICO: Semantic Clustering and Screenshot-Based Topic Classification. Journal of Advanced Computing Systems , 4(5), 67-83. https://doi.org/10.69987/JACS.2024.40506
Kizilcec, R. F. (2016). How much information? Effects of transparency on trust in an algorithmic interface. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 2390-2395. https://doi.org/10.1145/2858036.2858402
Lee, J. D., & See, K. A. (2004). Trust in automation: Designing for appropriate reliance. Human Factors, 46(1), 50-80. https://doi.org/10.1518/hfes.46.1.50_30392
Liao, Q. V., Gruen, D., & Miller, S. (2020). Questioning the AI: Informing design practices for explainable AI user experiences. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 1-15. https://doi.org/10.1145/3313831.3376590
Munzner, T. (2014). Visualization analysis and design. CRC Press.
National Institute of Standards and Technology. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0) (NIST AI 100-1). U.S. Department of Commerce. https://doi.org/10.6028/NIST.AI.100-1
Nielsen, J. (1994). Enhancing the explanatory power of usability heuristics. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 152-158. https://doi.org/10.1145/191666.191729
Public Company Accounting Oversight Board. (2024). AS 1105: Audit evidence. PCAOB.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you? Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135-1144. https://doi.org/10.1145/2939672.2939778
Shneiderman, B. (1996). The eyes have it: A task by data type taxonomy for information visualizations. Proceedings of the IEEE Symposium on Visual Languages, 336-343. https://doi.org/10.1109/VL.1996.545307
Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257-285. https://doi.org/10.1207/s15516709cog1202_4
Tufte, E. R. (2001). The visual display of quantitative information (2nd ed.). Graphics Press.
U.S. Securities and Exchange Commission. (2024a). Financial Statement Data Sets. https://www.sec.gov/data-research/sec-markets-data/financial-statement-data-sets
U.S. Securities and Exchange Commission. (2024b). Financial Statement Data Sets documentation. https://www.sec.gov/files/financial-statement-data-sets.pdf
U.S. Securities and Exchange Commission. (2024c). Financial Statement and Notes Data Sets. https://www.sec.gov/data-research/sec-markets-data/financial-statement-notes-data-sets
U.S. Securities and Exchange Commission. (2024d). EDGAR Application Programming Interfaces. https://www.sec.gov/search-filings/edgar-application-programming-interfaces
Ware, C. (2020). Information visualization: Perception for design (4th ed.). Morgan Kaufmann.
World Wide Web Consortium. (2023). Web Content Accessibility Guidelines (WCAG) 2.2. W3C Recommendation. https://www.w3.org/TR/WCAG22/
Yushan Chen, & Evelyn Chan. (2023). Multimodal UI Representation Learning: Ablation of Screenshot, Wireframe, and View-Hierarchy Proxies on an Uploaded 168-Screen Dataset. Journal of Advanced Computing Systems , 3(1), 1-15. https://doi.org/10.69987/JACS.2023.30101
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Kai Zhang, Yuanzheng Chen, Annie Qian
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
5.png)
