9 citations · 37 across the 32 of their papers we have counts for
33 papers
On the (Intuitionistic) Logic of Next-Token Prediction
Paul Tarau
We model in intuitionistic implicational logic the key enabler of today's GenerativeAI: the next-token prediction in autoregressive causal neural networks. In our framework, next-t…
Natlog: Embedding Logic Programming into the Python Deep-Learning Ecosystem
Paul Tarau
Driven by expressiveness commonalities of Python and our Python-based embedded logic-based language Natlog, we design high-level interaction patterns between equivalent language co…
Full Automation of Goal-driven LLM Dialog Threads with And-Or Recursors and Refiner Oracles
Paul Tarau
We automate deep step-by step reasoning in an LLM dialog thread by recursively exploring alternatives (OR-nodes) and expanding details (AND-nodes) up to a given depth. Starting fro…
A Gaze into the Internal Logic of Graph Neural Networks, with Logic
Paul Tarau
Graph Neural Networks share with Logic Programming several key relational inference mechanisms. The datasets on which they are trained and evaluated can be seen as database facts c…
Abductive Reasoning in Intuitionistic Propositional Logic via Theorem Synthesis
Paul Tarau
With help of a compact Prolog-based theorem prover for Intuitionistic Propositional Logic, we synthesize minimal assumptions under which a given formula formula becomes a theorem.…
Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch
Paul Tarau
We introduce Natlog, a lightweight Logic Programming language, sharing Prolog's unification-driven execution model, but with a simplified syntax and semantics. Our proof-of-concept…