From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement

TL;DR

This paper introduces a neurosymbolic method combining language models and Logic Tensor Networks to validate offer documents in regulated procurement, emphasizing interpretability and legal compliance.

Contribution

It presents a novel integration of symbolic and subsymbolic AI for factually correct, verifiable decisions with explainability in regulated settings.

Findings

Achieves performance comparable to existing models.

Enables rule checking and justification via predicate and rule truth values.

Offers improved interpretability and modularity for AI decision-making.

Abstract

We present a neurosymbolic approach, i.e., combining symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and then aggregate with an LTN (Logic Tensor Network) to make an auditable decision. In regulated public institutions, decisions must be made in a manner that is both factually correct and legally verifiable. Our neurosymbolic approach allows existing domain-specific knowledge to be linked to the semantic text understanding of language models. The decisions resulting from our pipeline can be justified by predicate values, rule truth values, and corresponding text passages, which enables rule checking based on a real corpus of offer documents. Our experiments on a real corpus show that the proposed pipeline achieves performance comparable to existing models, while its key advantage lies in its interpretability, modular predicate extraction, and explicit support for XAI (Explainable AI).