# FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification

arXiv: https://arxiv.org/abs/2604.23588 · HTML: https://mlsanity.com/paper/2604.23588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [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)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [Lynx: An Open Source Hallucination Evaluation Model](https://mlsanity.com/paper/2407.08488/) (2024)
- [Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination](https://mlsanity.com/paper/2311.15548/) (2023)
- [Chainpoll: A high efficacy method for LLM hallucination detection](https://mlsanity.com/paper/2310.18344/) (2023)
- [FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance](https://mlsanity.com/paper/2508.05201/) (2025)

## Built on by (most cited first, 4 of 4)

- [When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses](https://mlsanity.com/paper/2608.01619/) (2026)
- [When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis](https://mlsanity.com/paper/2606.29251/) (2026)
- [Confidence Estimation for Financial Vision-Language Models in Chart and Document Understanding](https://mlsanity.com/paper/2608.06532/) (2026)
- [CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA](https://mlsanity.com/paper/2608.13706/) (2026)

## Abstract (arXiv)

Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI Act's high-risk enforcement deadline approaches (August 2026). Existing hallucination detectors treat all claims uniformly, missing 43% of computational errors that require arithmetic re-verification against structured tables. We present FinGround, a three-stage verify-then-ground pipeline for financial document QA. Stage 1 performs finance-aware hybrid retrieval over text and tables. Stage 2 decomposes answers into atomic claims classified by a six-type financial taxonomy and verified with type-routed strategies including formula reconstruction. Stage 3 rewrites unsupported claims with paragraph- and table-cell-level citations. To cleanly isolate verification value from retrieval quality, we propose retrieval-equalized evaluation as standard methodology for RAG verification research: when all systems receive identical retrieval, FinGround still reduces hallucination rates by 68% over the strongest baseline (p < 0.01). The full pipeline achieves a 78% reduction relative to GPT-4o. An 8B distilled detector retains 91.4% F1 at 18x lower per-claim latency, enabling 0.003/query deployment, supported by qualitative signals from a four-week analyst pilot.