Metraipolis › archive › dc_579cbfe445e1

Measuring Hallucination in Large Language Models: A Probabilistic Study of Context Persistence Effects (2026) · DOI 10.3390/software5040045

Source: Metraipolis archive
Original: https://doi.org/10.3390/software5040045
License (as archived): CC-BY-4.0
Archived: 2026-10-26T15:59:54.904Z
SHA-256 of the archived text: ac5cdae008da5ea8b958bd3227b52f67d96d0fb45a12c6304c140a440cef06e9
Stable URL of this page: https://metraipolis.com/documento/dc_579cbfe445e1

How to cite

Measuring Hallucination in Large Language Models: A Probabilistic Study of Context Persistence Effects (2026) · DOI 10.3390/software5040045 — Metraipolis archive, https://doi.org/10.3390/software5040045 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_579cbfe445e1 (Metraipolis archive dc_579cbfe445e1, sha256 ac5cdae008da5ea8b958bd3227b52f67d96d0fb45a12c6304c140a440cef06e9)

BibTeX

@misc{dc579cbfe445e1,
  title = {Measuring Hallucination in Large Language Models: A Probabilistic Study of Context Persistence Effects (2026) · DOI 10.3390/software5040045},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.3390/software5040045},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_579cbfe445e1; sha256 ac5cdae008da5ea8b958bd3227b52f67d96d0fb45a12c6304c140a440cef06e9},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.3390/software5040045. 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 (journal-article).
Titolo: Measuring Hallucination in Large Language Models: A Probabilistic Study of Context Persistence Effects
Autori: Arhat Anil Dahiwale, Mithunvisvesh Sureshkumar, Sree Varun Manoj Kumar, Meera K. Nagendra Rao, Venkatesh Bajjareddy, Rashmi Mogenahalli Ranganath, Yuqing Lin
Pubblicato: 2026-10-24 · in: Software · editore: MDPI AG
DOI: https://doi.org/10.3390/software5040045
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
In this paper, a semi-deterministic approach is introduced for evaluating the answer-and-reasoning reliability of large language models using propositional logic and Bernoulli random variables. We focus on an operational class of hallucination defined by failures in final-answer correctness and/or reasoning validity, which is distinct from factuality hallucination involving fabricated world knowledge. Hallucination is represented as the logical negation of the conjunction of answer correctness and reasoning validity, enabling probabilistic evaluation. The framework was evaluated using Gemini 3.1 Pro and Claude Sonnet 5 on probability and random process (PRP) problems. For each model, 90 questions were presented in five cycles per condition, producing 450 responses per model-condition combination and 1800 responses in total. The Independent and Persistent conditions differed in conversational state, session structure, and question-order structure; therefore, observed differences are interpreted as condition-level associations. For Gemini 3.1 Pro, the hallucination probability increased from 20.44% to 36.22% (77.2% relative increase), while for Claude Sonnet 5, it increased from 22.44% to 36.22% (61.4% relative increase). A dependence-aware generalized estimating equation analysis estimated an odds ratio of 2.080 (95% robust CI [1.384, 3.127], p=4.264×10−4) for Persistent versus Independent conditions.

Fonte: https://api.crossref.org/works/10.3390%2Fsoftware5040045 — metadati Crossref, consultati il 2026-10-26. Interrogazione: «hallucination detection language models».