Article

Hallucination or confabulation? A psychological reinterpretation of erroneous outputs in large language models

2026-07-06

Abstract excerpt

<p>Large language models (LLMs) can generate fluent but false outputs that are widely described as “hallucinations.” We argue that this term is psychologically imprecise. In clinical psychology and psychiatry, hallucinations are perceptual phenomena, whereas many erroneous LLM outputs are better characterized as constructive, plausibility-guided responses produced under insufficient informational constraint. We su...

Topics

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

Identifiers and source

Literature Corpus work: f676b6dd-938b-50d4-998b-0430172268a6
DOI: 10.31234/osf.io/bqgk7_v2

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Hallucination or confabulation? A psychological reinterpretation of erroneous outputs in large language modelsDOI 10.31234/osf.io/bqgk7_v2Read

Hallucination as an Inevitable Byproduct of Intelligence in Large Language ModelsSemantic proximity Read

Rethinking Medical LLM Hallucinations: A System-Level SurveySemantic proximity Read

From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMsSemantic proximity Read

Advances in Reducing AI-Generated Hallucinations: Techniques and Open ChallengesSemantic proximity Read

Hallucination Is Inevitable for LLMs with the Open World AssumptionSemantic proximity Read

Enhancing Reliability in Large Language Models: Self-Detection of Hallucinations With Spontaneous Self-ChecksSemantic proximity Read

Understanding the Inner Workings of Large Language Models in MedicineSemantic proximity Read

Learning the Phenotype of Medical HallucinationsSemantic proximity Read

Artificial Intelligence in Mental Health Treatment and ResearchSemantic proximity Read

Discourse Structure as an Interpretable Signal for Detecting Hallucinated Chain-of-Thought Reasoning in Large Language ModelsSemantic proximity Read

Understanding the Inner Workings of Large Language Models in MedicineSemantic proximity Read

Mind the Gap: From Plausible to Valid Self-Explanations in Large Language ModelsSemantic proximity Read