Recent extensions of Datalog that consider the temporal dimension as a first-class citizen have unlocked the possibility of using its temporal variants, such as DatalogMTL, to model and reason about complex financial domains. Very relevant ones are crypto-activity markets, which, according to the recent Markets in Crypto-Assets Regulation (MiCAR) of the EU, are described by white papers published by crypto-assets issuers. In particular, the issuers publish semi-structured information about the assets they are willing to ofer. Then, the assets are implemented in decentralized finance contexts (i.e., in a blockchain) as executable scripts known as smart contracts. However, these scripts are often criticized for their complexity, which makes them challenging to understand and communicate. On the other hand, in our experience, the availability of a declarative and executable representation of a crypto-activity market fosters a better understanding of that market as well as improved transparency, reproducibility and, as a consequence, increased fairness. These characteristics are of major interest to the financial authorities for example for supervision purposes. In this paper, we study the problem of automatically translating textual descriptions of crypto-assets, written according to the MiCAR specifications, into DatalogMTL programs that represent and capture the respective crypto-activity market. To this end, we opt for a machine translation approach and leverage a Large Language Model. We discuss promising techniques and preliminary experimental results.
Knowledge Representation and Reasoning (KRR) formalisms, such as Datalog and its extensions, are
gathering increasing attention in industrial contexts. This is particularly evident in the financial sector,
with applications in the so-called Decentralized Finance (DeFi), a novel financial paradigm that leverages
distributed ledger technologies to ofer services without intermediaries. Logical languages such as
Datalog efectively balance expressive power and computational complexity, enabling, thanks to their
extension to the temporal dimension, the creation of concise and eficiently executable formalizations
of smart contracts, i.e., executable scripts that implement a financial asset [
A B C D E F G
Description
Information about the issuer Information about the e-money
token Information about the admission
to trading Rights and obligations of the token Information about the underlying
technology
Information on the risks Information on sustainability templates is appealing if combined with the impressive power of state-of-the-art Large Language Models (LLMs), which have proved to be capable of understanding and manipulating complex unstructured data as text. One of the most promising applications is using LLMs to analyze white papers, their compliance with rules, and their features, which may impact financial markets, raising the interest of ifnancial authorities.
Leveraging Large Language Models for the automatic translation of natural language descriptions into
executable code on a blockchain is a novel and unexplored field due to the challenges of (i) converting
text to programming languages an LLM has rarely seen, and (ii) ensuring the fidelity and quality of
the translated content [
Contribution. In this short work, we present our preliminary approach that aims at translating white papers into an executable and inherently transparent language as DatalogMTL. Our approach leverages the semi-structured format enforced by the MiCAR to build a pipeline that supports a pre-trained LLM agent in the translation task by (i) reducing the amount of information passed to the model, filtering in only specific sections of the white paper, and (ii) implementing token-specific pre- and post-processing steps that help the LLM achieve an executable output.
In this section, we briefly recall DatalogMTL foundations required for its use in crypto-activity modelling,
i.e., to model smart contracts. Then, we outline the main aspects of interest introduced by the MiCAR.
DatalogMTL. DatalogMTL [
The MiCA Regulation in the EU. The Markets in Crypto-Assets (MiCA) regulation, enacted by
the European Union, covers three categories: asset-referenced tokens, e-money tokens, and other
crypto-assets. Since the scope of the third category is broader, in this work we will focus only on the
ifrst two more specific tokens. For each crypto asset category, the MiCAR contains norms regarding the
content of the white paper. While no oficial template has been published yet, we report in Table 1 the
likely structure of the templates, following the consultations that are in progress [
The problem of translating an arbitrary NL whitepaper into a DatalogMTL specification is inherently complex and our experience shows that pure machine translation approaches, where the LLM is directly tasked with the NL-to-DatalogMTL translation goal (even when fine-tuning is involved) are not efective and lead to arbitrary programs, highly afected by hallucinations and overall incorrect. To overcome these dificulties, we suggest a paradigm shift and follow a template-based technique, implemented in the pipeline shown in Figure 1.
Overview. We pre-define a set of market mechanisms ℳ that represent standard “functional components” of a market, such as creation (minting), selling of a token (redemption), and so on. For each pattern, we feature pre-built templatized (i.e., with formal variables) DatalogMTL rules decorated with a natural language description. Examples are in Figure 2. Then, given a white paper, we can first select the templatized rules according to the token type, and iteratively prompt the LLM with all the information required to specialize the rules to the white paper content.
LLM-based Rules Specialization. Algorithm 1 describes the process we developed to adapt the generic rules to the token-specific features. Based on a custom input MiCAR-compliant white paper, the corresponding set of templatized rules Σ, either e-money token or asset-referenced token, is considered. Then, for each market mechanism of the set ℳ of mechanisms (line 1), we consider the set of templatized rules , their description that we have pre-defined, and we extract the portion of the white paper that contains relevant information for the mechanism (lines 2-4). Each mechanism is also decorated with a set of keywords , which describe the content of the mechanism and activate optional pre-processing steps (lines 5-7). Thus, if the mechanism deals with one of the topics defined by the keywords, a pre-processing LLM call will be performed to rewrite the information that was inserted in the white paper fields. The aim of this step is to support the LLM-translation task by simplifying, if possible, the textual input. For instance, this is the case of temporal information such as the specification of market opening days, which can be defined in multiple formats, e.g., the market is closed on weekends. Then, the LLM is provided , and and is prompted to perform the actual specification (line 8): “These are Datalog rules: {R} where {D}. Modify them according to this information: {I}” Finally, the LLM generates the translated rules, and we perform post-processing checks (line 9-11), such as detection of syntax or programmatically identifiable errors. In case checks are not passed, the LLM is asked to repeat the task until they are passed. Mechanism
Algorithm 1 Rules Specialization.
1: for ∀ ∈ ℳ do 2: ← Σ .GetRules(M ) 3: ← Σ .GetDescription(M ) 4: ← WhitePaper .GetRelevantFields(M ) 5: if M .Keywords ∈ then 6: ← LLMRewrite() 7: end if 8: * ← LLMPrompt (, , ) 9: while * .ℎ not passed do 10: * ← (, , ) 11: end while 12: end for ◁ For each Token’s Market Mechanism
◁ Get generalized DatalogMTL rules ◁ Get the description for the mechanism variables ◁ Query the Textual Information from the White Paper ◁ Mechanism deals with a topic requiring pre-processing
◁ LLM is asked to rewrite the information ◁ LLM is prompted to adapt the rules R according to I ◁ LLM is asked to repeat the task
For our preliminary experiments and tests, we employed a pre-trained LLaMA 3 70B as our reference LLM. The model was prompted with system content providing a generic DatalogMTL adaptation example. We opted not to perform fine-tuning since (i) few-shot learning demonstrated promising results in our initial trials, and (ii) there is a current lack of large-scale datasets of DatalogMTL rules. Example 1 (X-Coin - Supported Blockchain). Consider the market mechanism = Transfer for a hypothetical e-money token named X-Coin. It defines the conditions required by the white paper for the approval of a transfer of tokens between a Sender and a Receiver of units on the blockchain . For instance, suppose the only main conditions for approving a transfer are (i) having enough tokens in the sender’s balance, and (ii) that the transfer occurs on a supported blockchain. Figure 3 illustrates the pipeline in action for the Transfer mechanism. In this example, the variable 1 (refer to Figure 2) has been instantiated and the model has also created additional rules to account for the multiple blockchains, i.e., inserting OR conditions. To achieve this, the input has been automatically pre-processed: since the mechanism referred to the supported blockchain technology, a step to separate each blockchain type has been activated. Then, post-processing checks have controlled the syntax in the output, such as the presence of all initial predicates and the absence of additional undesired predicates.
DatalogMTL Market Formalization. By collecting all the rules that have been generated or modified
in Algorithm 1, we can create a DatalogMTL program that formalizes the token’s specific market that, if
extensional facts are injected, is executable in a DatalogMTL engine. Full examples of our approach over
existing crypto activities, converting natural language white papers into a DatalogMTL formalization,
can be found in our repository [
Discussion and Limitations. We developed the pipeline with the goal of producing DatalogMTL
programs that are executable in any reasoner engine that supports the MTL extension of Datalog.
Thus, engines like the MeTeoR [
Finally, while the semantic correctness of the resulting programs can be evaluated using rule-based checks or domain-specific constraints, which involve detecting rule-specific features, assessing the content correctness is more challenging. Specifically, verifying that the translated rules, including potential errors introduced by the LLM, accurately replicate the mechanisms of a specific token remains dificult, particularly in an automated way. In fact, although employing human evaluators seems like a straightforward solution, automatic checks and correctness experiments would require a gold standard, i.e., the true sets of market rules, which is so far unavailable. Nevertheless, our pipeline is strictly guided, with the presence of specific regulations and pre-defined rule templates that mitigate the issue of creating unreliable DatalogMTL representations of crypto-markets.
In this work, we presented the first approach that, by employing the enormous power of pre-trained LLMs in a controlled fashion, tries to model crypto activity markets in a tractable and inherently transparent formal language, i.e., DatalogMTL. Preliminary results show that we can automatically generate executable DatalogMTL programs starting from white papers in natural language by carefully instructing the LLM to perform the translation task and by leveraging the semi-structured nature of the MiCAR. In future works, we will expand on this approach and industrialize it on a larger scale, allowing stakeholders to get a DatalogMTL formalization of any MiCAR-compliant token. We will also test whether such programs fully replicate the markets by simulating their evolution and comparing it with the real market they aim to represent.
This work has been funded by the Vienna Science and Technology Fund (WWTF) [10.47379/VRG18013, 10.47379/NXT22018, 10.47379/ICT2201]. The views expressed in the paper are those of the authors and do not necessarily reflect those of the Bank of Italy.