What question did this study set out to answer?

The research aims to explore the interactions between large language models and automated theorem proving systems in the context of legal reasoning.

February 24, 2026Open Access

A Multimodal AI System: Comparing LLMs and Theorem Proving Systems

View Full Paper

Ask AI

Bookmark

Authors

Compares automated theorem proving and LLMs in legal reasoning, suggesting insights for broader applications.

The research aims to explore the interactions between large language models and automated theorem proving systems in the context of legal reasoning.
Applied logical model theory and Löwenheim–Skolem theorems to compare two AI modalities.
Developed a first-order logic theorem-proving system to perform legal reasoning.
Utilized LLMs to analyze user tax queries and transform them for the theorem-proving system.
Found an equivalence between laws represented in logic and semantics provided by LLMs.
Demonstrated that LLMs can enhance user input/output for the theorem-proving system.
Highlighted the roles of syntactic proofs and logical semantics in legal reasoning.

Bradford et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark