---
title: "Knowledge graphs and rules for compliance (research idea)"
description: "Knowledge graphs appear on 141 recent papers and neuro-symbolic AI on 14, almost all in AI journals; only 34 of 481 such papers concern accounting, tax, legal, regulatory, financial or audit uses. Compliance is a domain of explicit rules and entities, which language models alone handle badly. Do graphs and symbolic rules make them reliable enough for audits and tax?"
url: https://scholar4ai.com/ideas/knowledge-graphs-for-compliance
markdown_url: https://scholar4ai.com/ideas/knowledge-graphs-for-compliance.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "Knowledge graphs appear on 141 recent papers and neuro-symbolic AI on 14, almost all in AI journals; only 34 of 481 such papers concern accounting, tax, legal, regulatory, financial or audit uses."
date: "2026-10-23"
updated: "2026-10-23"
status: "seed"
tags: ["ai", "accounting", "law"]
keywords: ["knowledge graphs", "neuro-symbolic AI", "regulatory compliance"]
---

# Knowledge graphs and rules for compliance

Knowledge graphs appear on 141 recent papers and neuro-symbolic AI on 14, almost all in AI journals; only 34 of 481 such papers concern accounting, tax, legal, regulatory, financial or audit uses. Compliance is a domain of explicit rules and entities, which language models alone handle badly. Do graphs and symbolic rules make them reliable enough for audits and tax?

## What prompted this

Since October 2025, 481 papers carry a knowledge-graph, neuro-symbolic, symbolic-reasoning, rule-based, ontology, formal-verification or logical-reasoning keyword (451 in AI journals): "knowledge graphs" on 141, "knowledge graph completion" on 41, "temporal knowledge graphs" on 38, "neuro-symbolic AI" on 14, "symbolic reasoning" on 8. Only 34 of the 481 also carry an accounting, tax, legal, regulatory, compliance, finance, contract, audit, law, bank, fraud or anti-money-laundering keyword, although "regulatory compliance" appears on 60 papers in the archive.

## Questions

- On tasks such as checking a transaction against sanctions lists and ownership chains, or applying a tax rule to a set of facts, do systems that combine a language model with a knowledge graph and explicit rules make fewer errors than the model alone, and are their errors explainable?
- How much effort does it take to keep the rules and graphs current when regulations change, and who maintains them?
- Would auditors and regulators accept outputs with symbolic justifications where they reject model-only outputs?

## Data that could help

Public regulatory texts and sanctions lists, company ownership graphs (Open Ownership, Orbis), and test cases with known answers from tax and compliance training materials.

## Next step

Build a benchmark of 200 compliance cases (sanctions screening with ownership chains, tax rule application) and compare a language model alone with the same model backed by a graph and rules.

## Related research activity

*The keywords this note follows, in the tracked finance, accounting, economics, management, operations research and AI journals as of 2026-10-26*

| Keyword | Papers, last 30 days | Rank | Papers per month, Oct 23 – Oct 26* | Papers, last 36 months |
|---|---:|---:|---|---:|
| knowledge graphs | 9 | #149 | 3, 6, 8, 8, 11, 6, 7, 11, 5, 8, 12, 12, 4, 10, 15, 7, 14, 14, 10, 4, 16, 23, 12, 10, 9, 18, 15, 14, 15, 12, 19, 10, 9, 14, 13, 12, 9 | 396 |
| neuro-symbolic AI | 2 | #1303 | 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 2, 0, 0, 1, 0, 0, 1, 2, 0, 1, 1, 4, 1, 1, 1, 1, 2 | 22 |
| regulatory compliance | 5 | #393 | 0, 1, 0, 3, 1, 1, 1, 1, 3, 2, 1, 3, 2, 2, 3, 4, 2, 7, 3, 5, 3, 5, 7, 5, 2, 6, 5, 6, 7, 7, 8, 5, 7, 7, 1, 1, 4 | 127 |

## Cite this page

Scholar4AI. (2026). Knowledge graphs and rules for compliance. Journal Research Rankings. Retrieved October 23, 2026, from https://scholar4ai.com/ideas/knowledge-graphs-for-compliance

```bibtex
@misc{scholar4ai-ideas-knowledge-graphs-for-compliance,
  author = {{Scholar4AI}},
  title = {Knowledge graphs and rules for compliance},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/ideas/knowledge-graphs-for-compliance}},
  urldate = {2026-10-23},
  note = {Journal Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).