Journal article · 2025 · Open access
Detection of Hallucinations Based on the Internal States of Large Language Models
Automatic Documentation and Mathematical Linguistics, 28(6), 1282–1305 · Published 1 December 2025 · DOI 10.3103/s0005105525701456
In brief
“Detection of Hallucinations Based on the Internal States of Large Language Models” is a 2025 journal article by Timur Rustemovich Aisin and Tatiana Vyacheslavovna Shamardina, published in Automatic Documentation and Mathematical Linguistics. OpenAlex counts 3 citations as of 15 November 2026, which puts it in the top 4% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Russian Digital Libraries Journal.
- Citations
- 3
- Most cited in
- 2026 (3)
- Field-weighted impact
- 0.73
- References
- 26
- Authors
- 2
Abstract
In recent years, large language models (LLMs) have achieved substantial progress in natural language processing tasks and have become key instruments for addressing a wide range of applied and research problems. However, as their scale and capabilities grow, the issue of hallucinations — i.e., the generation of false, unreliable, or nonexistent information presented in a credible manner—has become increasingly acute. Consequently, analyzing the nature of hallucinations and developing methods for their detection has acquired both scientific and practical significance. This study examines the phenomenon of hallucinations in large language models, reviews their existing classification, and investigates potential causes. Using the Flan-T5 model, we analyze differences in the model’s internal states when generating hallucinations versus correct responses. Based on these discrepancies, we propose two approaches for hallucination detection: one leveraging attention maps and the other utilizing the model’s hidden states. These methods are evaluated on data from HaluEval and Shroom 2024 benchmarks in tasks such as summarization, question answering, paraphrasing, machine translation, and definition generation. Additionally, we assess the transferability of the trained detectors across different hallucination types, in order to evaluate the robustness of the proposed methods.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Aisin, T. R., & Shamardina, T. V. (2025). Detection of Hallucinations Based on the Internal States of Large Language Models. Automatic Documentation and Mathematical Linguistics, 28(6), 1282–1305. https://doi.org/10.3103/s0005105525701456
MLA 9
Aisin, Timur Rustemovich, and Tatiana Vyacheslavovna Shamardina. “Detection of Hallucinations Based on the Internal States of Large Language Models.” Automatic Documentation and Mathematical Linguistics, vol. 28, no. 6, 2025, pp. 1282–1305. https://doi.org/10.3103/s0005105525701456.
Chicago
Aisin, Timur Rustemovich and Tatiana Vyacheslavovna Shamardina. 2025. “Detection of Hallucinations Based on the Internal States of Large Language Models.” Automatic Documentation and Mathematical Linguistics 28 (6): 1282–1305. https://doi.org/10.3103/s0005105525701456.
Harvard
Aisin, T. R. and Shamardina, T. V. (2025) ‘Detection of Hallucinations Based on the Internal States of Large Language Models’, Automatic Documentation and Mathematical Linguistics, 28(6), pp. 1282–1305. doi:10.3103/s0005105525701456.
IEEE
T. R. Aisin and T. V. Shamardina, “Detection of Hallucinations Based on the Internal States of Large Language Models,” Automatic Documentation and Mathematical Linguistics, vol. 28, no. 6, pp. 1282–1305, 2025, doi: 10.3103/s0005105525701456.
BibTeX
@article{aisin2025detection,
title = {{Detection of Hallucinations Based on the Internal States of Large Language Models}},
author = {Aisin, Timur Rustemovich and Shamardina, Tatiana Vyacheslavovna},
journal = {Automatic Documentation and Mathematical Linguistics},
year = {2025},
volume = {28},
number = {6},
pages = {1282--1305},
doi = {10.3103/s0005105525701456},
url = {https://doi.org/10.3103/s0005105525701456}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- hallucination detection
- large language models
- internal state
- hidden states
- attention maps
- Flan-T5
- HaluEval
- summarization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Aisin, T. R., & Shamardina, T. V. (2025). Detection of Hallucinations Based on the Internal States of Large Language Models. Automatic Documentation and Mathematical Linguistics, 28(6), 1282–1305. https://doi.org/10.3103/s0005105525701456
How many times has this paper been cited?
3 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Russian Digital Libraries Journal.
Who wrote this paper?
Timur Rustemovich Aisin, Tatiana Vyacheslavovna Shamardina.
What is the DOI of this paper?
10.3103/s0005105525701456. The permanent link is https://doi.org/10.3103/s0005105525701456.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.