From the journal

Citation-Grounded Answers for EU Financial Regulation: The Design and Measured Grounding of Licentium Compass

Ground each answer in the words of the law. Verify each quote against the source. Refuse when the text is silent. Every sentence carries a link to the provision it rests on. That is what separates an answer that sounds correct from one a lawyer can audit in a click.

Illia ProkopievCo-Founder and CEO5 min read

Ground each answer in the words of the law. Verify each quote against the source. Refuse when the text is silent. Every sentence carries a link to the provision it rests on. That is what separates an answer that sounds correct from one a lawyer can audit in a click.

Hallucination

A general language model answers regulatory questions in seconds, and it may be wrong. Stanford’s RegLab tested the leading legal-AI tools built on retrieval. It found wrong or unsupported answers in 17 to 33 percent of cases (Magesh et al. 2025). The problem did not go away. A 2026 study checked generated legal citations against a court citation graph. It still found 13 to 21 percent of them fabricated, misapplied, or out of date (Ovcharov 2026).

Licentium Compass answers questions on EU financial, crypto, and AI regulation from the text of the law, and it shows the exact provision behind each sentence. When its corpus does not hold the answer, it says so.

No sentence without a quote you can check

Licentium Compass pulls candidate provisions from its automatically updated corpus, writes an answer bound to those provisions, then checks every quoted span character by character against the primary source. A span that is not an exact substring of the cited article is dropped and flagged. The citation a reader sees is built from the original database record for that provision: instrument, article number, canonical reference. The model never writes the article number itself. So it cannot invent a citation or pin a real quote to the wrong article.

This check sits outside the writing step. It is a second gate, and it runs the same way every time. On a set of hard, multi-provision questions, every citation Licentium Compass displayed passed the character-level check: a 100 percent verbatim rate. On the same set, the system declined to answer questions outside its corpus instead of inventing support.

Primary law, kept current

Licentium Compass reads statutes, not summaries of them. Its corpus holds the consolidated text of the acts that govern this area: MiCA, EMIR, DORA, the AML Regulation, the sixth AML Directive, the Transfer of Funds Regulation, the AI Act, the Digital Services Act, the Data Act, and others. That is 54 instruments and more than 4,400 article-level provisions in English. Each provision is stored with a hash of its source text, so a change in the official version is detectable.

Law does not stand still. Licentium Compass records which consolidated version of each act it holds and the date of that version. When the EU publishes a newer consolidation, or when an amending act carries a date later than the version on file, Licentium Compass marks that act for refresh. Answers stay tied to the text in force. Recent work treats this timing as its own test of a citation: whether the provision was valid on the relevant date. Licentium Compass tracks versions for exactly that check.

A map of cross-references

Articles point at other articles. One procedure article gets invoked by dozens of provisions across separate regulations. Licentium Compass reads these internal citations and stores them as links: 20,138 connections from one provision to another across the corpus. A reader who opens a cited article sees the provisions it refers to, so a chain of duties is visible.

From a product to its duties, by rule, not by guess

Some questions are not about what a statute says. They ask what applies to a given business. A custody service, a stablecoin issuer, and a deployer of high-risk AI each face a different set of duties. For these, Licentium Compass runs a fixed mapping. A short intake describes the product. A set of rules turns that description into the provisions to verify, each tied to a cited article. Each rule carries a version, so a change to a rule is a new version on record.

Measuring the grounding

Licentium Compass scores its own answers. A question set with known-correct provisions runs through the full pipeline. The scoring is mechanical: whether each displayed citation quotes the source word for word, whether the cited provisions include the expected ones, and whether the system abstains on questions outside the corpus. The word-for-word pass rate reached 100 percent on the most recent run. Recall against the expected provisions is the harder number, and it is where current tuning is aimed. Naming both is the point: a grounding claim means little without the abstention rate and the miss rate beside it.

Sources

Magesh, V., Surani, F., Dahl, M., Suzgun, M., Manning, C. D., and Ho, D. E. (2025). Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools. Journal of Empirical Legal Studies.

Ovcharov, V. (2026). Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs. arXiv:2606.00898.

Ju, Y.-J., and Lee, S.-W. (2026). Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering. arXiv:2605.29742.

Illia Prokopiev

Written by

Illia Prokopiev

Co-Founder and CEO

Illia is the Managing Partner and founder of Licentium. With over 11 years of practice, he has guided innovators through cross-border M&A deals and the disputes that follow, combining transactional skill with courtroom resolve. Admitted to the bar in 2017, he pivoted early to Web3, serving as legal advisor to prominent crypto projects and carrying AML/MLRO duties that anchored complex token, DAO, and compliance questions on solid regulatory ground. Certified in money laundering prevention and an active crypto investor, Illia blends market intuition with a global network of specialists, enabling Licentium to untangle licensing knots for crypto and AI ventures anywhere in the world.

More from the journal

See all

Finland Gambling Act Ends State Monopoly, Opens Licensed iGaming Market from July 2027

Finland's Gambling Act, approved by the President on 16 January 2026, ends the state monopoly held by Veikkaus Oy and introduces competitive licensing for private iGaming operators in online sports betting and casino verticals. The Finnish Gambling Authority accepts licence applications from 1 March 2026; licensed market operations begin 1 July 2027. Licensed operators pay a flat gross-gaming-revenue tax of 22%.

SEC Adds Regulation Crypto to Rulemaking Agenda with Token Safe Harbor, July 2026

On 7 July 2026, the U.S. Securities and Exchange Commission placed Regulation Crypto on its regulatory priority agenda, the first crypto-specific rulemaking in the agency's history under Chair Paul Atkins. The proposal would create a time-limited registration exemption for early-stage token projects, permit capital raises up to $75 million in a 12-month period, and establish a decentralisation safe harbor for tokens whose issuers have ceased all essential managerial efforts.

Delaware Enacts Stablecoin Modernization Package Aligning State Licensing with Federal GENIUS Act

Delaware Governor Matt Meyer signed the Banking, Money Transmission, and Stablecoin Modernization Package on 6 July 2026, creating a state licensing regime for payment stablecoin issuers under the Delaware Payment Stablecoin Act. Senate Bill 19 establishes reserve requirements, redemption standards, and capital obligations aligned with the federal GENIUS Act and directs the Commissioner of Banks to seek nationwide operating authority through a substantial-similarity certification.