Paper Detail

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan

arxiv Score 20.3

Published 2026-08-17 · First seen 2026-08-18

General AI

Abstract

Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{shu2026lava,
  title = {LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing},
  author = {Ruoqi Shu and Xuhui Wang and Isaac Wang and Yanming Mai and Bo Wan},
  year = {2026},
  abstract = {Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic },
  url = {https://arxiv.org/abs/2608.16763},
  keywords = {cs.AI},
  eprint = {2608.16763},
  archiveprefix = {arXiv},
}

Metadata

{}