NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework

arXiv:2604.24612v1 Announce Type: new Abstract: ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax, enabling its knowledge bases to be used directly across a wide range of neurosymbolic systems. The original specification endows this syntax with three pairwise independent semantics: classical, fuzzy, and probabilistic, each accompanied by dedicated semantic rules. We show that these seemingly disparate semantics are all instances of one categorical framework based on monads, the very construct that models side effects in functional programming. This enables the modular addition of new semantics and systematic translations between them. As example, we outline the addition of generalised quantification in Logic Tensor Networks (LTN) to arbitrary (also infinite) domains by extending the Giry monad to probability spaces. In particular, our approach allows a modular implementation of ULLER in Python and Haskell, of which we have published initial versions on GitHub.

Related

• OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
• CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
• TAPO-Description Logic for Information Behavior: Refined OBoxes, Inference, and Categorical Semantics
• ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning
• Syntax Is Easy, Semantics Is Hard: Evaluating LLMs for LTL Translation
• Plausible Reasoning and First-Order Plausible Logic

Source: arXiv cs.AI | 2026-04-28