Article

Artificial Intelligence and Metacognitive Knowledge: LLMs Can Report Decision Weights as Faithfully as Humans in Multi-Attribute Choice

2026-08-25

Abstract excerpt

<p>Users have become increasingly reliant on Large Language Models (LLMs) to complete a wide range of reasoning tasks, from managing workplace projects to giving personal advice. However, LLMs function as black boxes, leaving users with minimal insight into how they generate the responses that they do. One way that users can attempt to peek into these black boxes is by asking LLMs to explain their reasoning proces...

Topics

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

Uncategorized literature

Identifiers and source

Literature Corpus work: 08662182-a9a3-5401-b5e9-c9cef37ec0ca
DOI: 10.31234/osf.io/zq6md_v2

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Artificial Intelligence and Metacognitive Knowledge: LLMs Can Report Decision Weights as Faithfully as Humans in Multi-Attribute ChoiceDOI 10.31234/osf.io/zq6md_v2Read

Worth the Weight: Modern LLMs Demonstrate Accurate Metacognitive Knowledge of Decision Weights in Multi-Attribute ChoiceSemantic proximity Read

Nonlinear Transformation of Probabilities by Large Language ModelsSemantic proximity Read

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

AI-assisted discovery of unknown cognitive biases: Humans systematically undervalue information under complexitySemantic proximity Read

Generating options and choosing between them rely on distinct forms of value representationSemantic proximity Read

The advice gap: adaptive yet suboptimal advice integrationSemantic proximity Read

Uncovering the Computational Mechanisms Underlying Many-Alternative ChoiceSemantic proximity Read

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

LLM-generated possibilities increase blame attributionSemantic proximity Read

Is ChatGPT Humanly Irrational?Semantic proximity Read

Emergent Behavioural Signatures in Large Language Models: A Cross-Task Study of Risk and Forecasting BehaviourSemantic proximity Read