Article

Hallucination Is Inevitable for LLMs with the Open World Assumption

2025-10-10

Abstract excerpt

Large Language Models (LLMs) exhibit impressive linguistic competence but also produce inaccurate or fabricated outputs, often called “hallucinations”. Engineering approaches usually regard hallucination as a defect to be minimized, while formal analyses have argued for its theoretical inevitability. Yet both perspectives remain incomplete when considering the conditions required for artificial general intelligenc...

Topics

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

Identifiers and source

Literature Corpus work: f7e9bc13-b882-5889-823a-80a6621d020d
DOI: 10.20944/preprints202510.0689.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Hallucination Is Inevitable for LLMs with the Open World AssumptionDOI 10.20944/preprints202510.0689.v1Read

Hallucination or confabulation? A psychological reinterpretation of erroneous outputs in large language modelsSemantic proximity Read

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

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

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

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

Failure Geometry as a Constructive Control Paradigm for Large Language Models Attractor-Driven Semantic Collapse Under Hard Termination ConstraintsSemantic proximity Read

A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity Read

A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity Read

Comprehensive Review of AI Hallucinations: Impacts and Mitigation Strategies for Financial and Business ApplicationsSemantic proximity Read

The boredom trap: How LLMs are draining entropy from the way we communicateSemantic proximity Read

Knowledge Accuracy and Reducing Hallucinations in LLMs via Dynamic Domain Knowledge InjectionSemantic proximity Read

Sparse Autoencoders as an Interpretable Interface for LLM Development and ControlSemantic proximity Read