Article

Probabilistic Reasoning with Transformer Networks: An Application to Predicate Judgment

2022-12-20

Abstract excerpt

<p>Transformer networks that are trained on participant-generated feature norms have been shown to replicate several behavioral patterns observed in prior research on human semantic cognition. In this paper, I compare the predictions of these networks with participant evaluations of sentences sampled from a vast domain of discourse, with thousands of naturalistic predicates. I find that existing transformer networ...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 32fc3a4b-fb84-5904-ac78-e2dc84788165
DOI: 10.31234/osf.io/s3d74

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Probabilistic Reasoning with Transformer Networks: An Application to Predicate JudgmentDOI 10.31234/osf.io/s3d74Read

Transformer Networks of Human Conceptual KnowledgeSemantic proximity Read

Do people use counterexamples or subjective probabilities in uncertain conditional reasoning? Investigating human reasoning with an open response formatSemantic proximity Read

Epistemic Bridge Protocol: Regulating Epistemic Commitment in Probabilistic Generative AgentsSemantic proximity Read

Learning Representations by Humans, for HumansSemantic proximity Read

Evidence from Formal Logical Reasoning Reveals that the Language of Thought is not Natural LanguageSemantic proximity Read

Epistemological Fault Lines Between Human and Artificial IntelligenceSemantic proximity Read

A human brain network specialized for abstract formal reasoningSemantic proximity Read

Data-Driven Construction of Individualized Process Models for Human ReasoningSemantic proximity Read

Studying and improving reasoning in humans and machinesSemantic proximity Read

Inductive reasoning in minds and machinesSemantic proximity Read

Human-like property induction is a challenge for large language modelsSemantic proximity Read

Using AI Uncertainty Quantification to Improve Human Decision-MakingSemantic proximity Read