An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making

• URL: http://arxiv.org/abs/2601.00142v1
• Date: Thu, 01 Jan 2026 00:07:37 GMT
• Title: An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making
• Abstract summary: This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning.<n>We show that reasoning via supervised learning is less appealing than reasoning via explicit model construction.<n>We propose a new version of Sphere Neural Networks that embeds concepts as circles on the surface of an n-dimensional sphere.
• Score: 29.42914503379841
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning. LLMs remain unreliable and struggle with simple decision-making that animals can master without extensive corpora training. Through disjunctive syllogistic reasoning testing, we show that reasoning via supervised learning is less appealing than reasoning via explicit model construction. Concretely, we show that an Euler Net trained to achieve 100.00% in classic syllogistic reasoning can be trained to reach 100.00% accuracy in disjunctive syllogistic reasoning. However, the retrained Euler Net suffers severely from catastrophic forgetting (its performance drops to 6.25% on already-learned classic syllogistic reasoning), and its reasoning competence is limited to the pattern level. We propose a new version of Sphere Neural Networks that embeds concepts as circles on the surface of an n-dimensional sphere. These Sphere Neural Networks enable the representation of the negation operator via complement circles and achieve reliable decision-making by filtering out illogical statements that form unsatisfiable circular configurations. We demonstrate that the Sphere Neural Network can master 16 syllogistic reasoning tasks, including rigorous disjunctive syllogistic reasoning, while preserving the rigour of classical syllogistic reasoning. We conclude that neural reasoning with explicit model construction is the most reliable among the three methodological categories of neural reasoning.

Related papers

• Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic [3.421904493396495]
  We investigate the logical generalization capabilities of pre-trained large language models (LLMs) using the syllogistic fragment as a benchmark.<n>We propose a hybrid architecture integrating symbolic reasoning with neural computation.<n>Our experiments show that high efficiency is preserved even with relatively small neural components.
  arXiv  Detail & Related papers  (2025-10-10T15:27:29Z)
• Learning to Reason via Mixture-of-Thought for Logical Reasoning [56.24256916896427]
  Mixture-of-Thought (MoT) is a framework that enables LLMs to reason across three complementary modalities: natural language, code, and truth-table.<n>MoT adopts a two-phase design: (1) self-evolving MoT training, which jointly learns from filtered, self-generated rationales across modalities; and (2) MoT inference, which fully leverages the synergy of three modalities to produce better predictions.
  arXiv  Detail & Related papers  (2025-05-21T17:59:54Z)
• Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset [5.695579108997392]
  This paper explores the question of how accurately current large language models can perform logical reasoning in natural language. We present a syllogism dataset called NeuBAROCO, which consists of syllogistic reasoning problems in English and Japanese. Our experiments with leading large language models indicate that these models exhibit reasoning biases similar to humans, along with other error tendencies.
  arXiv  Detail & Related papers  (2024-08-08T12:10:50Z)
• A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences [5.141416267381492]
  We consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. We investigate the effects of chain-of-thought reasoning, in-context learning, and supervised fine-tuning on syllogistic reasoning. Our results suggest that the behavior of pre-trained LLMs can be explained by cognitive science.
  arXiv  Detail & Related papers  (2024-06-17T08:59:04Z)
• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• Sphere Neural-Networks for Rational Reasoning [24.591858077975548]
  We present a novel extension by generalising computational building blocks from vectors to spheres.<n>We propose Sphere Neural Networks (SphNNs) for human-like reasoning through model construction and inspection.<n>SphNNs can evolve into various types of reasoning, such as rationality-temporal reasoning, logical reasoning with negation and disjunction, event reasoning, neuro-symbolic unification, and humour understanding.
  arXiv  Detail & Related papers  (2024-03-22T15:44:59Z)
• Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual Learning [2.912595438026074]
  We show that by combining a neural-symbolic system with methods from continual learning, Logic Networks can obtain a higher level of accuracy. Continual learning is added to LTNs by adopting a curriculum of learning from knowledge and data with recall. Results indicate significant improvement on the non-monotonic reasoning problem.
  arXiv  Detail & Related papers  (2023-05-03T15:11:34Z)
• MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure [129.8481568648651]
  We propose a benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Based on the multi-hop chain of reasoning, the explanation form includes three main components. We evaluate the current best models' performance on this new explanation form.
  arXiv  Detail & Related papers  (2022-10-22T16:01:13Z)
• Reinforcement Learning with External Knowledge by using Logical Neural Networks [67.46162586940905]
  A recent neuro-symbolic framework called the Logical Neural Networks (LNNs) can simultaneously provide key-properties of both neural networks and symbolic logic. We propose an integrated method that enables model-free reinforcement learning from external knowledge sources.
  arXiv  Detail & Related papers  (2021-03-03T12:34:59Z)
• Neural Logic Reasoning [47.622957656745356]
  We propose Logic-Integrated Neural Network (LINN) to integrate the power of deep learning and logic reasoning. LINN learns basic logical operations such as AND, OR, NOT as neural modules, and conducts propositional logical reasoning through the network for inference. Experiments show that LINN significantly outperforms state-of-the-art recommendation models in Top-K recommendation.
  arXiv  Detail & Related papers  (2020-08-20T14:53:23Z)
• Logical Neural Networks [51.46602187496816]
  We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning) Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omni rather than focused on predefined target variables, and corresponds to logical reasoning.
  arXiv  Detail & Related papers  (2020-06-23T16:55:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.