3 papers
cs.CL2026
Modeling Next-Token Prediction as Left-Nested Intuitionistic Implication
Paul Tarau
We introduce the \emph{Arrow Language Model}, a neural architecture derived from an intuitionistic-logic interpretation of next-token prediction. Instead of representing tokens as…
cs.AI2025
On LLM-generated Logic Programs and their Inference Execution Methods
Paul Tarau
Large Language Models (LLMs) trained on petabytes of data are highly compressed repositories of a significant proportion of the knowledge accumulated and distilled so far. In this…
cs.CL2024
Through the Looking Glass, and what Horn Clause Programs Found There
Paul Tarau
Dual Horn clauses mirror key properties of Horn clauses. This paper explores the ``other side of the looking glass'' to reveal some expected and unexpected symmetries and their pra…