# FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification

arXiv: https://arxiv.org/abs/2605.29586 · HTML: https://mlsanity.com/paper/2605.29586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 23 of 23)

- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents](https://mlsanity.com/paper/2311.09805/) (2023)
- [Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination](https://mlsanity.com/paper/2311.15548/) (2023)
- [FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains](https://mlsanity.com/paper/2311.09797/) (2023)
- [FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging](https://mlsanity.com/paper/2506.05828/) (2025)
- [FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents](https://mlsanity.com/paper/2411.05764/) (2024)
- [FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs](https://mlsanity.com/paper/2510.08886/) (2025)
- [FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance](https://mlsanity.com/paper/2508.05201/) (2025)
- [Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings](https://mlsanity.com/paper/2602.07294/) (2026)
- [Expect the Unexpected: FailSafe Long Context QA for Finance](https://mlsanity.com/paper/2502.06329/) (2025)
- [SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities](https://mlsanity.com/paper/2504.04596/) (2025)
- [Automating Financial Statement Audits with Large Language Models](https://mlsanity.com/paper/2506.17282/) (2025)
- [FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets](https://mlsanity.com/paper/2603.07316/) (2026)
- [FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking](https://mlsanity.com/paper/2511.19671/) (2025)
- [Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector](https://mlsanity.com/paper/2603.04663/) (2026)
- [Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial Reasoning](https://mlsanity.com/paper/2601.21157/) (2026)

## Abstract (arXiv)

We introduce FinVerBench, a benchmark and validity study for financial statement verification: determining whether a set of corporate financial statements is numerically consistent from the information shown to the model. FinVerBench is built from SEC 10-K XBRL filings for 43 S&P 500 companies and defines a four-category error taxonomy covering arithmetic, cross-statement linkage, year-over-year, and magnitude perturbations. We attempt fifteen contemporary LLM evaluations and report fourteen complete runs; a Gemini 2.5 Pro run is excluded from the main comparison because 40/108 gateway calls failed. All binary metrics exclude underdetermined positive instances whose perturbed line item is not rendered, leaving a 105-instance observable diagnostic subset (43 clean, 62 error-injected). Under the original guided-checklist prompt on the unrounded diagnostic subset, nine of fourteen complete LLM runs produce 95-100% false positives on clean statements, while one run achieves 0% observed false positives. Benchmark rendering choices materially affect measured recall: on a realistic rounded variant of the same observable subset, the calibrated model's recall is 79.0% with 0% observed FPR, compared with 100.0% recall on the unrounded diagnostic variant. These results support a construct-validity conclusion rather than a final leaderboard: financial statement verification is not merely arithmetic detection, but calibrated judgment under incomplete observability, prompt-induced assumptions, and realistic numerical rendering. FinVerBench and all code are publicly available.