Metraipolis › archive › dc_220be58d049b

Hallucination in Large Language Models: Epistemic Status, Detection, and Validation Criteria in Higher Education (2026) · DOI 10.20944/preprints202609.1992.v1

Source
Metraipolis archive
Original
https://doi.org/10.20944/preprints202609.1992.v1
License (as archived)
CC-BY-4.0
Archived
2026-10-08T04:27:14.465Z
SHA-256 of the archived text
67db37a3ea3169ffffd43d2e2149be65c330bee1e33fcde5bfec5c8e081eb1d4
Stable URL of this page
https://metraipolis.com/documento/dc_220be58d049b

How to cite

Hallucination in Large Language Models: Epistemic Status, Detection, and Validation Criteria in Higher Education (2026) · DOI 10.20944/preprints202609.1992.v1 — Metraipolis archive, https://doi.org/10.20944/preprints202609.1992.v1 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_220be58d049b (Metraipolis archive dc_220be58d049b, sha256 67db37a3ea3169ffffd43d2e2149be65c330bee1e33fcde5bfec5c8e081eb1d4)
BibTeX
@misc{dc220be58d049b,
  title = {Hallucination in Large Language Models: Epistemic Status, Detection, and Validation Criteria in Higher Education (2026) · DOI 10.20944/preprints202609.1992.v1},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.20944/preprints202609.1992.v1},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_220be58d049b; sha256 67db37a3ea3169ffffd43d2e2149be65c330bee1e33fcde5bfec5c8e081eb1d4},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.20944/preprints202609.1992.v1. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Articolo recente con licenza aperta: scheda dai metadati Crossref (posted-content).
Titolo: Hallucination in Large Language Models: Epistemic Status, Detection, and Validation Criteria in Higher Education
Autori: William Orlando Cárdenas Marín, Rubén Darío Morales Rojas
Pubblicato: 2026-09-23 · editore: MDPI AG
DOI: https://doi.org/10.20944/preprints202609.1992.v1
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
False statements produced by a language model arrive with the same confident form as true ones, with no mark to guide verification, and this indistinction bears fully on the university classroom. This article reviews the peer-reviewed literature under a declared protocol that retained thirty-two works and one continuously updated resource, drawn from technical research on detection, epistemology, cognitive psychology, critical thinking, and educational research. The argument starts from an epistemic and functional characterization of the system, to which we attribute the lack of access of its own to the output and of a criterion of truth of its own, whence it follows that every correction comes from a reference external to the generative process, which we call external anchoring. On that basis, the classes of divergence are ordered according to whether they are measured against facts about the world or against the material supplied by the user, the detection procedures are reviewed together with their declared limits, and four criteria applicable from a public interface are formulated, grouped into two families and crossed with the typology in a table. The closing sections examine two effects on the reader, cognitive satisfaction and the externalization of epistemic vigilance, and the institutional conditions that their correction demands.

Fonte: https://api.crossref.org/works/10.20944%2Fpreprints202609.1992.v1 — metadati Crossref, consultati il 2026-10-07. Interrogazione: «hallucination detection language models».