Induction and Inquiry via Probabilistic Reasoning over Language and Code

• URL: http://arxiv.org/abs/2609.01815v1
• Date: Tue, 01 Sep 2026 19:44:18 GMT
• Title: Induction and Inquiry via Probabilistic Reasoning over Language and Code
• Abstract summary: How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science.<n>Here we introduce a computational model that captures these three properties, by encoding symbolic knowledge as mental programs that combine natural language with source code.<n>Across a range of behavioral studies this model successfully reproduces quantitative signatures of human inductive learning and active inquiry.
• Score: 14.649285579019358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and compute-efficient, (2) capture gradations of uncertainty to support intelligent inquiry and information gathering, and (3) be flexible enough to mentally represent the endless range of concepts people can learn and think about. Here we introduce a computational model that captures these three properties, by encoding symbolic knowledge as mental programs that combine natural language with source code, and sequentially inferring mental programs using LLM-guided Bayesian learning algorithms. Across a range of behavioral studies this model successfully reproduces quantitative signatures of human inductive learning and active inquiry, such as anchoring, garden-pathing, and other effects. In contrast, pure LLMs and classic Bayesian models either fail at the underlying task, or do not reproduce human behavior, or succeed only at exorbitant computational cost. These results suggest that one way humans continually grow their knowledge is by mentally representing many hypotheses spanning language-like and program-like representations, then revising those hypotheses to approximate Bayesian updates, while a bottom-up neural mechanism (an LLM) makes inference both tractable and learnable.

Related papers

• Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation? [45.36751031924419]
  An essential problem in artificial intelligence is whether LLMs can simulate human cognition or merely imitate surface-level behaviors.<n>We introduce a benchmark grounded in the longitudinal research trajectories of 217 researchers across diverse domains of artificial intelligence.<n>A multidimensional cognitive alignment metric is proposed to assess individual-level cognitive consistency.
  arXiv  Detail & Related papers  (2026-03-29T13:44:55Z)
• LLMs model how humans induce logically structured rules [18.202446211409548]
  A long-standing debate concerns the adequacy of artificial neural networks as computational models.<n>Recent advances in neural networks -- specifically, the advent of large language models (LLMs) -- represent an important shift in this debate.<n>We argue that LLMs may instantiate a novel theoretical account of the primitive representations and computations necessary to explain human logical concepts.
  arXiv  Detail & Related papers  (2025-07-05T03:24:18Z)
• General Intelligence Requires Reward-based Pretraining [14.057301560895505]
  Large Language Models (LLMs) have demonstrated impressive real-world utility.<n>But their ability to reason adaptively and robustly remains fragile.<n>We propose disangling knowledge and reasoning through three key directions.
  arXiv  Detail & Related papers  (2025-02-26T18:51:12Z)
• Neuron-based Personality Trait Induction in Large Language Models [115.08894603023712]
  Large language models (LLMs) have become increasingly proficient at simulating various personality traits. We present a neuron-based approach for personality trait induction in LLMs.
  arXiv  Detail & Related papers  (2024-10-16T07:47:45Z)
• Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice [4.029252551781513]
  We propose a novel way to enhance the utility of Large Language Models as cognitive models.<n>We show that an LLM pretrained on an ecologically valid arithmetic dataset, predicts human behavior better than many traditional cognitive models.
  arXiv  Detail & Related papers  (2024-05-29T17:37:14Z)
• Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? [140.9751389452011]
  We study the biases of large language models (LLMs) in relation to those known in children when solving arithmetic word problems. We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features.
  arXiv  Detail & Related papers  (2024-01-31T18:48:20Z)
• Brain-inspired Computational Intelligence via Predictive Coding [73.42407863671565]
  Predictive coding (PC) has shown promising properties that make it potentially valuable for the machine learning community.<n>PC-like algorithms are starting to be present in multiple sub-fields of machine learning and AI at large.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
  We unify encoder and decoder-based models into a single prefix-LM. For learning methods, we explore the claim of a "free lunch" hypothesis. For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
  arXiv  Detail & Related papers  (2023-05-03T17:55:25Z)
• ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT [72.83383437501577]
  Large language models (LLMs) have recently demonstrated significant potential in mathematical abilities. LLMs currently have difficulty in bridging perception, language understanding and reasoning capabilities. This paper presents a novel method for integrating LLMs into the abductive learning framework.
  arXiv  Detail & Related papers  (2023-04-21T16:23:47Z)
• Scallop: A Language for Neurosymbolic Programming [14.148819428748597]
  Scallop is a language that combines the benefits of deep learning and logical reasoning. It is capable of expressing algorithmic reasoning in diverse and challenging AI tasks. It provides a succinct interface for machine learning programmers to integrate logical domain knowledge.
  arXiv  Detail & Related papers  (2023-04-10T18:46:53Z)
• Toward a realistic model of speech processing in the brain with self-supervised learning [67.7130239674153]
  Self-supervised algorithms trained on the raw waveform constitute a promising candidate. We show that Wav2Vec 2.0 learns brain-like representations with as little as 600 hours of unlabelled speech.
  arXiv  Detail & Related papers  (2022-06-03T17:01:46Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)

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.