AI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture

• URL: http://arxiv.org/abs/2603.22561v1
• Date: Mon, 23 Mar 2026 20:44:38 GMT
• Title: AI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture
• Abstract summary: This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a syllogistic reasoning benchmark.<n>Experiment 1 evaluates a direct neural baseline for predicting full 9-way human response distributions under 5-fold cross-validation.<n>Experiment 2 introduces a bounded dual-path architecture with separate intuition and deliberation pathways, motivated by computational mental-model theory.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing debates about world models and multi-stage reasoning in AI. It provides a controlled setting for testing whether a learned system can develop structured internal computation rather than only one-shot associative prediction. Experiment 1 evaluates a direct neural baseline for predicting full 9-way human response distributions under 5-fold cross-validation. Experiment 2 introduces a bounded dual-path architecture with separate intuition and deliberation pathways, motivated by computational mental-model theory (Khemlani & Johnson-Laird, 2022). Under cross-validation, bounded intuition reaches an aggregate correlation of r = 0.7272, whereas bounded deliberation reaches r = 0.8152, and the deliberation advantage is significant across folds (p = 0.0101). The largest held-out gains occur for NVC, Eca, and Oca, suggesting improved handling of rejection responses and c-a conclusions. A canonical 80:20 interpretability run and a five-seed stability sweep further indicate that the deliberation pathway develops sparse, differentiated internal structure, including an Oac-leaning state, a dominant workhorse state, and several weakly used or unused states whose exact indices vary across runs. These findings are consistent with reasoning-like internal organization under bounded conditions, while stopping short of any claim that the model reproduces full sequential processes of model construction, counterexample search, and conclusion revision.

Related papers

• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs [4.5194910739268925]
  ThinkProbe is a framework for structural analysis of reasoning traces.<n>It converts each trace into a Thought Graph with cycles, 8 node types, and 6 edge types.<n>ThinkProbe reveals that reasoning structure is a stable, model-level property.
  arXiv  Detail & Related papers  (2026-06-27T19:56:55Z)
• Neural Bayesian Sequential Routing [0.0]
  We introduce textbfNeural Bayesian Sequential Routing (NBSR), a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG)<n>NBSR achieves competitive predictive performance while providing transparent routing traces, path-dependent evidence attribution, uncertainty-aware decision control, and resource-rational inference.<n>Overall, NBSR offers a mathematically grounded framework for interpretable, modular, and resource-rational agentic AI.
  arXiv  Detail & Related papers  (2026-05-22T22:45:56Z)
• Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning [0.0]
  Children learn that shape is the kind of feature that tends to define object categories.<n>We trained autoregressive transformer language models on synthetic corpora.<n>Models rely on frame-to-feature template matching rather than structured noun-to-domain-to-feature abstraction.
  arXiv  Detail & Related papers  (2026-04-06T23:11:25Z)
• On the Limits of Interpretable Machine Learning in Quintic Root Classification [0.0]
  We test an extensive set of Machine Learning models, including decision trees, logistic regression, support vector machines, random forest, gradient boosting, XGBoost, symbolic regression, and neural networks.<n>We find no evidence that the evaluated ML models autonomously recover discrete, human-interpretable mathematical rules from raw coefficients.<n>These results suggest that, in structured mathematical domains, interpretability may require explicit structural inductive bias rather than purely data-driven approximation.
  arXiv  Detail & Related papers  (2026-02-26T19:53:41Z)
• The Catastrophic Paradox of Human Cognitive Frameworks in Large Language Model Evaluation: A Comprehensive Empirical Analysis of the CHC-LLM Incompatibility [0.0]
  Models achieving above-average human IQ scores simultaneously exhibit binary accuracy rates approaching zero on crystallized knowledge tasks.<n>This disconnect appears most strongly in the crystallized intelligence domain.<n>We propose a framework for developing native machine cognition assessments that recognize the non-human nature of artificial intelligence.
  arXiv  Detail & Related papers  (2025-11-23T05:49:57Z)
• ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction [70.53044880892196]
  We introduce a novel task named Latent Reasoning Chain Extraction (ARCHE), in which models must decompose complex reasoning arguments into combinations of standard reasoning paradigms in the form of a Reasoning Logic Tree (RLT)<n>To facilitate this task, we release ARCHE Bench, a new benchmark derived from 70 Nature Communications articles, including more than 1,900 references and 38,000 viewpoints.<n> Evaluations on 10 leading LLMs on ARCHE Bench reveal that models exhibit a trade-off between REA and EC, and none are yet able to extract a complete and standard reasoning chain.
  arXiv  Detail & Related papers  (2025-11-16T07:37:09Z)
• Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
  We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
  arXiv  Detail & Related papers  (2025-11-13T07:26:01Z)
• STRIDE: Subset-Free Functional Decomposition for XAI in Tabular Settings [0.0]
  We present STRIDE, a framework that answers "what" features are important but fails to reveal "how" they interact.<n>We also introduce "component surgery", a diagnostic that isolates a learned interaction and quantifies its contribution.
  arXiv  Detail & Related papers  (2025-09-11T00:19:53Z)
• Efficient Computation of Counterfactual Bounds [44.4263314637532]
  We compute exact counterfactual bounds via algorithms for credal nets on a subclass of structural causal models. We evaluate their accuracy by providing credible intervals on the quality of the approximation.
  arXiv  Detail & Related papers  (2023-07-17T07:59:47Z)
• Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models [15.817239008727789]
  In this work, we analyze a specific type of causal query called domain counterfactuals, which hypothesizes what a sample would have looked like if it had been generated in a different domain. We show that recovering the latent Structural Causal Model (SCM) is unnecessary for estimating domain counterfactuals. We also develop a theoretically grounded practical algorithm that simplifies the modeling process to generative model estimation.
  arXiv  Detail & Related papers  (2023-06-20T04:19:06Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Neural Causal Models for Counterfactual Identification and Estimation [62.30444687707919]
  We study the evaluation of counterfactual statements through neural models. First, we show that neural causal models (NCMs) are expressive enough. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions.
  arXiv  Detail & Related papers  (2022-09-30T18:29:09Z)
• Neural Unification for Logic Reasoning over Natural Language [0.28675177318965034]
  Automated Theorem Proving deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules) Recent approaches have proposed transformer-based architectures for deriving conjectures given axioms expressed in natural language (English) In this work we propose a new architecture, namely the Neural Unifier, which achieves state-of-the-art results in term of generalisation.
  arXiv  Detail & Related papers  (2021-09-17T10:48:39Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)

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.