Syllogistic Reasoning

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Non-Zero Radius: The Missing Component of Neural Networks
Oct 29, 2026Tiansi Dong, Mateja Jamnik, Pietro LiòSyllogistic Reasoning Logical Reasoning
Computer Lab, The University of Cambridge · The Alan Turing Institute
Do Diagrams Help Large Language Models Reason? Evidence from Syllogistic Reasoning
Jul 26, 2026Risako Ando, Koji MineshimaLLM Evaluation LLM Reasoning
Keio University, 2-15-45 Mita, Minato-ku, Tokyo 108-8345, Japan
Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
Jul 22, 2026Hanna Abi Akl, Fabien Gandon, Catherine Faron +1Knowledge Representation Structured Reasoning
Université Côte d’Azur, Inria, CNRS, I3S, Sophia Antipolis, France · Data ScienceTech Institute, Paris, France
Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes
Jul 20, 2026Brian K ChenSyllogistic Reasoning Logical Reasoning
National University of Singapore
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law
Jun 24, 2026Tiansi Dong, Mateja Jamnik, Pietro LiòSyllogistic Reasoning Logical Reasoning
The Alan Turing Institute, 96 Euston Road, London, NW1 2DB, UK. · Department of Computer Science and Technology, University of Cambridge, 15 JJ Thomson Ave., Cambridge, CB3 0FD, UK.
SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance
Jun 8, 2026Hanna Abi Akl, Fabien Gandon, Catherine Faron +1Language Model Bias Evaluation Logical Reasoning
Université Côte d’Azur, Inria, CNRS, I3S, Sophia Antipolis, France · Data ScienceTech Institute, Paris, France
UFAL-CUNI at SemEval-2026 Task 11: An Efficient Modular Neuro-symbolic Method for Syllogistic Reasoning
May 6, 2026Ivan Kartáč, Kristýna Onderková, Jan Bronec +3Syllogistic Reasoning Logical Reasoning
Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University
FregeLogic at SemEval 2026 Task 11: A Hybrid Neuro-Symbolic Architecture for Content-Robust Syllogistic Validity Prediction
Apr 20, 2026Adewale Akinfaderin, Nafi DialloSyllogistic Reasoning Logical Reasoning
Amazon Web Services Seattle, WA
AI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture
Mar 23, 2026Laurence AnthonySyllogistic Reasoning Logical Reasoning
School of Creative Science and Engineering Faculty of Science and Engineering Waseda University
Abductive Reasoning with Syllogistic Forms in Large Language Models
Mar 6, 2026Hirohiko Abe, Risako Ando, Takanobu Morishita Kentaro Ozeki +2Syllogistic Reasoning Abductive Reasoning in Language Models
Keio University, Tokyo, Japan · The University of Tokyo, Tokyo, Japan

Oct 29, 2026J/K move · Enter open · S save

Non-Zero Radius: The Missing Component of Neural Networks

Tiansi Dong, Mateja Jamnik, Pietro Liò

Computer Lab, The University of Cambridge · The Alan Turing Institute

Syllogistic Reasoning Logical Reasoning Neuro-Symbolic Reasoning Neural Representation Geometry Hyperspherical Representation Learning

Open paper AskPDF arXiv

Inspired by the analogy between the all-or-none activation of biological neurons and the true-false of logic circuits, McCulloch and Pitts proposed a mathematical model of the biological neuron in 1943 with the aim of simulating logical reasoning. Although Norbert Wiener considered the model overly simplistic at the time, it later became a building block of modern neural networks, including large language models. Despite their remarkable empirical success, however, conventional neural networks remain largely black-box systems and struggle with reliable symbolic reasoning. Viewing vectors as spheres of zero radius, we relax the zero-radius constraint and represent concepts as spheres with non-zero radii. We argue that sphere-based representations can capture additional features of biological cognition, including representing spatial concepts as regions and reasoning through model construction and inspection. Building on sphere embeddings, we introduce Sphere Neural Networks (SphNNs), which use a transition map to achieve symbolic-level Aristotelian syllogistic reasoning without training data, thereby taking an initial step toward the original goal of McCulloch and Pitts. We suggest that the zero-radius constraint may reflect an aspect of the oversimplification identified by Wiener and may limit conventional neural networks' capacity for symbolic-level logical reasoning.