LLM-based DatalogMTL Modelling of MiCAR-compliant Crypto-Assets Markets

Abstract

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 offer. 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.