FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures
This solves the semantic alignment and verification challenge for financial analysts and regulators dealing with heterogeneous reporting regimes across jurisdictions, though it appears incremental as it builds on existing LLM-based extraction methods.
The paper tackles the problem of cross-jurisdiction financial reporting by addressing structural differences in accounting taxonomies and tagging infrastructures, presenting FinReporting, an agentic workflow that improves consistency and reliability in annual filings from the US, Japan, and China.
Financial reporting systems increasingly use large language models (LLMs) to extract and summarize corporate disclosures. However, most assume a single-market setting and do not address structural differences across jurisdictions. Variations in accounting taxonomies, tagging infrastructures (e.g., XBRL vs. PDF), and aggregation conventions make cross-jurisdiction reporting a semantic alignment and verification challenge. We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting. The system builds a unified canonical ontology over Income Statement, Balance Sheet, and Cash Flow, and decomposes reporting into auditable stages including filing acquisition, extraction, canonical mapping, and anomaly logging. Rather than using LLMs as free-form generators, FinReporting deploys them as constrained verifiers under explicit decision rules and evidence grounding. Evaluated on annual filings from the US, Japan, and China, the system improves consistency and reliability under heterogeneous reporting regimes. We release an interactive demo supporting cross-market inspection and structured export of localized financial statements. Our demo is available at https://huggingface.co/spaces/BoomQ/FinReporting-Demo . The video describing our system is available at https://www.youtube.com/watch?v=f65jdEL31Kk