FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification

• URL: http://arxiv.org/abs/2604.23588v1
• Date: Sun, 26 Apr 2026 07:52:59 GMT
• Title: FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification
• Abstract summary: FinGround is a verify-then-ground pipeline for financial document QA.<n> Stage 1 performs finance-aware hybrid retrieval over text and tables.<n> Stage 2 decomposes answers into atomic claims classified by a six-type financial taxonomy.<n> Stage 3 rewrites unsupported claims with paragraph- and table-cell-level citations.
• Score: 13.891522069967507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications [52.570108663867046]
  A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation.<n>We study the codification readiness of implementation-facing research-method specifications, defined by whether they provide sufficient methodological information for a competent implementer or coding agent to construct the intended method without unsupported assumptions.<n>We introduce IdeaAMBIG, a benchmark of 660 evidence-grounded instances: 163 real-world gaps from reports and GitHub issues, and 497 controlled synthetic gaps injected into codification-ready references.
  arXiv  Detail & Related papers  (2026-09-09T17:59:04Z)
• FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents [45.708389696454304]
  FinHarness wraps a finance agent end-to-end with three components.<n>Fired risk factors are re-injected into the agent input as ex-ante evidence, enabling the agent to refuse, re-plan, or approve on its own.
  arXiv  Detail & Related papers  (2026-05-26T17:41:01Z)
• FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking [0.6356558256426569]
  We present a unified data-efficient framework for training large language models (LLMs)<n>We optimize answer quality, citation grounding, calibrated and refusal under real-world deployment constraints.<n>The system is deployed at 40+ financial institutions, achieving a 7.1 percentage point improvement in query resolution.
  arXiv  Detail & Related papers  (2026-05-06T22:04:44Z)
• Agentic Retrieval-Augmented Generation for Financial Document Question Answering [7.56842616602779]
  FinAgent-RAG is an agentic RAG framework that orchestrates iterative retrieval-reasoning loops with self-verification.<n>It integrates a Contrastive Financial Retriever trained with hard negative mining to distinguish semantically similar but numerically distinct financial passages.<n>It achieves 76.81%, 78.46%, and 74.96% execution accuracy respectively, outperforming the strongest baseline by 5.62--9.32 percentage points.
  arXiv  Detail & Related papers  (2026-05-06T19:59:51Z)
• ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection [13.891522069967507]
  Financial institutions track over 60,000 regulatory events annually.<n>The industry has paid over USD 300 billion in fines and settlements since the 2008 financial crisis.<n>We present ComplianceNLP, an end-to-end system that automatically monitors regulatory changes, extracts structured obligations, and identifies compliance gaps.
  arXiv  Detail & Related papers  (2026-04-26T07:44:50Z)
• AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking [13.891522069967507]
  We present AgentEval, a framework that formalizes agent executions as evaluation directed acyclic graphs (DAGs)<n>AgentEval achieves 2.17x higher failure detection recall than end-to-end evaluation and 72% root cause accuracy against an 81% human ceiling.
  arXiv  Detail & Related papers  (2026-04-26T07:38:47Z)
• One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness [12.183451602438753]
  We show that simple lexical constraints (banning a single punctuation character or common word) cause instruction-tuned LLMs to collapse their responses.<n>We show that base models show no systematic collapse under identical constraints, with effects that are small, noisy, and bidirectional.
  arXiv  Detail & Related papers  (2026-04-14T17:40:01Z)
• Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection [0.0]
  Budget-Sensitive Discovery Score (BSDS) penalizes false discoveries at each budget level.<n>Discovery Quality Score (DQS) provides a single summary statistic that no proposer can inflate by performing well at a cherry-picked budget.<n> framework applies to any setting where candidates are selected under budget constraints and asymmetric error costs.
  arXiv  Detail & Related papers  (2026-03-12T18:09:53Z)
• FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems [0.0]
  Current Knowledge Graph (KG)-augmented QA systems lack systematic mechanisms to detect hallucinations.<n>We introduce FinBench-QA-Hallucination, a benchmark for evaluating hallucination detection methods in KG-augmented financial QA over SEC 10-K filings.<n>Our findings highlight vulnerabilities in current KG-augmented systems and provide insights for building reliable financial information systems.
  arXiv  Detail & Related papers  (2026-03-11T04:37:53Z)
• Evaluating LLMs in Finance Requires Explicit Bias Consideration [88.38155218924999]
  Finance-specific biases can inflate performance, contaminate backtests, and make reported results useless for deployment claims.<n>No single bias is discussed in more than 28 percent of studies.<n>We propose a Structural Validity Framework and an evaluation checklist with minimal requirements for bias diagnosis and future system design.
  arXiv  Detail & Related papers  (2026-02-15T17:02:01Z)
• LLM-based Triplet Extraction from Financial Reports [39.146761527401424]
  We present a semi-automated pipeline for Subject-Predicate-Object triplet extraction using Ontology Conformance and Faithfulness metrics.<n>We also propose a hybrid verification strategy that combines matching with an LLM-as-a-judge check, reducing apparent subject hallucination rates from 65.2% to 1.6%.
  arXiv  Detail & Related papers  (2026-02-12T12:36:10Z)
• PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering [71.15346406323827]
  We introduce PRIME, a benchmark for evaluating verifiers on Process-Outcome Alignment verification.<n>We find that current verifiers frequently fail to detect derivation flaws.<n>We propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
  arXiv  Detail & Related papers  (2026-02-12T04:45:01Z)
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving [65.02106674311908]
  This paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning.<n>By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces.<n> Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists.
  arXiv  Detail & Related papers  (2025-12-11T15:26:28Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• AGENTICT$^2$S:Robust Text-to-SPARQL via Agentic Collaborative Reasoning over Heterogeneous Knowledge Graphs for the Circular Economy [42.73610751710192]
  AgenticT$2$S is a framework that decomposes knowledge graphs into subtasks managed by specialized agents.<n>A two-stage verifier detects structurally invalid and semantically underspecified queries.<n>Experiments on real-world circular economy KGs demonstrate that AgenticT$2$S improves execution accuracy by 17.3%.
  arXiv  Detail & Related papers  (2025-08-03T15:58:54Z)
• Precise Information Control in Long-Form Text Generation [107.83171105517863]
  We propose Precise Information Control (PIC), a new task formulation that requires models to generate long-form outputs grounded in a provided set of short self-contained statements.<n> PIC includes a full setting that tests a model's ability to include exactly all input claims, and a partial setting that requires the model to selectively incorporate only relevant claims.<n>We present PIC-Bench, a benchmark of eight long-form generation tasks adapted to the PIC setting, where LMs are supplied with well-formed, verifiable input claims.
  arXiv  Detail & Related papers  (2025-06-06T23:42:42Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
  Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.