Paper: arXiv 2508.17906
Authors: Abhinav Arun, Fabrizio Dimino, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali
Abstract
The financial domain poses unique challenges for knowledge graph (KG) construction at scale due to the complexity and regulatory nature of financial documents. Despite the critical importance of structured financial knowledge, the field lacks large-scale, open-source datasets capturing rich semantic relationships from corporate disclosures. We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S and P 100 companies - a comprehensive resource designed to catalyze research in financial AI. We propose a robust and generalizable knowledge graph (KG) construction framework that integrates intelligent document parsing, table-aware chunking, and schema-guided iterative extraction with a reflection-driven feedback loop. Our system incorporates a comprehensive evaluation pipeline, combining rule-based checks, statistical validation, and LLM-as-a-Judge assessments to holistically measure extraction quality. We support three extraction modes - single-pass, multi-pass, and reflection-agent-based - allowing flexible trade-offs between efficiency, accuracy, and reliability based on user requirements. Empirical evaluations demonstrate that the reflection-agent-based mode consistently achieves the best balance, attaining a 64.8 percent compliance score against all rule-based policies (CheckRules) and outperforming baseline methods (single-pass and multi-pass) across key metrics such as precision, comprehensiveness, and relevance in LLM-guided evaluations.
Complexity vs Empirical Score
- Math Complexity: 1.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper is highly empirical, presenting a specific framework for building and evaluating a financial knowledge graph dataset with multiple metrics (precision, compliance scores) and real-world data (SEC 10-K filings). The mathematics involved is primarily algorithmic and structural rather than dense theoretical derivations.
Research Flowchart
flowchart TD A["Research Goal<br>Create Financial KG & Framework"] --> B["Data Input<br>SEC 10-K Filings"] B --> C["Process<br>Schema-Guided Extraction"] C --> D["Output<br>Agentic KG Construction"] D --> E["Evaluation<br>Multi-Modal Validation"] E --> F["Outcome<br>FinReflectKG Dataset"] F --> G["Key Finding<br>Reflection-Agent achieves 64.8% compliance"] G --> H["Impact<br>Open-Source Financial Data Infrastructure"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes an open-source large-scale financial knowledge graph dataset built from SEC 10-K filings of all S&P 100 companies and a robust, generalizable KG construction framework with three extraction modes and a reflection-driven feedback loop.
Source sentence
We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S&P 100 companies - a comprehensive resource designed to catalyze research in financial AI.
Assumes
No explicit assumptions found in the text.
Data
- Financial KG dataset from SEC 10-K filings of all S&P 100 companies fundamentals public
Source sentence
We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S&P 100 companies
Costs
Not applicable
Finds 1
- The reflection-agent-based extraction mode consistently achieves the best balance, attaining a 64.8% compliance score against all rule-based policies (CheckRules) and outperforms baseline single-pass and multi-pass modes across precision, comprehensiveness, an performance
Source sentence
the reflection-agent-based mode consistently achieves the best balance, attaining a 64.8% compliance score against all rule-based policies (CheckRules) and outperforming baseline methods (single-pass & multi-pass) across key metrics such as precision, comprehensiveness, and relevance in LLM-guided evaluations.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 5 related papers). Coverage is partial, so this is neither replication nor refutation.
3 papers in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.