Journal article · 2023 · Open access

Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms

Arjun Malhotra, Rina Putri Santoso

International journal of statistics · Published 3 May 2023 · DOI 10.55640/ijs-03-01-02

Read the free full textView at the publisherCite this paper

In brief

“Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms” is a 2023 journal article by Arjun Malhotra and Rina Putri Santoso, published in International journal of statistics. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at International journal of statistics.

Citations
0
Authors
2

Abstract

Large Language Models (LLMs) have rapidly transitioned from experimental research artifacts to widely deployed socio-technical systems used in journalism, law, education, healthcare, and scientific research. Alongside their demonstrated fluency and versatility, these models exhibit a persistent and consequential limitation: hallucination, broadly understood as the generation of content that is syntactically plausible but factually incorrect, unverifiable, or internally inconsistent. High-profile incidents—including fabricated legal precedents, false accusations against real individuals, and erroneous scientific claims—have underscored the real-world risks associated with unmitigated hallucinations. This article provides a comprehensive, system-level examination of hallucinations in LLMs, synthesizing empirical case studies, theoretical taxonomies, detection methodologies, mitigation strategies, and evaluation frameworks. Drawing on recent academic literature and documented failures in deployed systems, the paper categorizes hallucinations into factual, logical, contextual, and self-contradictory forms, and analyzes their underlying mechanisms in model training, prompting, and deployment contexts. Particular emphasis is placed on black-box and zero-resource detection approaches, including SelfCheckGPT, Chain-of-Thought consistency methods, and alignment-based evaluation metrics such as GPTScore, GEval, and AlignScore. The discussion critically examines the limitations of current benchmarks and the epistemic challenges of evaluating truthfulness in generative systems. The article concludes by outlining open research challenges and ethical considerations, arguing that hallucination mitigation should be framed not as a problem of complete elimination, but as a continuous risk-management process integrating technical, institutional, and human-in-the-loop safeguards.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Malhotra, A., & Santoso, R. P. (2023). Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms. International journal of statistics. https://doi.org/10.55640/ijs-03-01-02

MLA 9

Malhotra, Arjun, and Rina Putri Santoso. “Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms.” International journal of statistics, 2023. https://doi.org/10.55640/ijs-03-01-02.

Chicago

Malhotra, Arjun and Rina Putri Santoso. 2023. “Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms.” International journal of statistics. https://doi.org/10.55640/ijs-03-01-02.

Harvard

Malhotra, A. and Santoso, R. P. (2023) ‘Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms’, International journal of statistics. doi:10.55640/ijs-03-01-02.

IEEE

A. Malhotra and R. P. Santoso, “Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms,” International journal of statistics, 2023, doi: 10.55640/ijs-03-01-02.

BibTeX

@article{malhotra2023mitigating,
  title     = {{Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms}},
  author    = {Malhotra, Arjun and Santoso, Rina Putri},
  journal   = {International journal of statistics},
  year      = {2023},
  doi       = {10.55640/ijs-03-01-02},
  url       = {https://doi.org/10.55640/ijs-03-01-02}
}

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 mitigation
  • large language models
  • hallucination detection
  • factual hallucination
  • hallucination taxonomy
  • black-box detection
  • benchmark limitations
  • human-in-the-loop

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Malhotra, A., & Santoso, R. P. (2023). Mitigating Hallucinations in Large Language Models: Taxonomies, Detection Frameworks, and Evaluation Paradigms. International journal of statistics. https://doi.org/10.55640/ijs-03-01-02

How many times has this paper been cited?

0 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 International journal of statistics.

Who wrote this paper?

Arjun Malhotra, Rina Putri Santoso.

What is the DOI of this paper?

10.55640/ijs-03-01-02. The permanent link is https://doi.org/10.55640/ijs-03-01-02.

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.