Journal article · 2025 · Open access

Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review

Sanjay Kumar

Journal of Information Systems Engineering & Management, 10(60s), 435–443 · Published 30 September 2025 · DOI 10.52783/jisem.v10i60s.13133

Free PDFView at the publisherCite this paper

In brief

“Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review” is a 2025 journal article by Sanjay Kumar, published in Journal of Information Systems Engineering & Management. 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: the full text is free to read at Journal of Information Systems Engineering & Management.

Citations
3
Most cited in
2026 (3)
Field-weighted impact
0.73
References
6
Authors
1

Abstract

Large Language Models have achieved unprecedented capabilities in natural language generation but remain vulnerable to hallucinations—outputs that are fluent and plausible yet factually incorrect or ungrounded. This comprehensive review examines the current landscape of hallucination detection and mitigation in LLMs, analyzing the theoretical foundations, detection methodologies, and mitigation strategies that have emerged to address this critical challenge. To explore the fundamental taxonomy distinguishing intrinsic hallucinations that deviate from input content from extrinsic hallucinations that contradict real-world facts, while examining how these manifestations vary across different natural language generation tasks. The review synthesizes five primary detection approaches including uncertainty estimation, attention pattern analysis, self-consistency checks, external fact verification, and trained evaluators, each offering unique advantages for identifying hallucinated content. To analyze mitigation strategies at both architectural levels through techniques like retrieval-augmented generation, tool integration, and factual fine-tuning, and systemic levels through guardrails, fallback policies, and human oversight. The evaluation landscape is examined through diverse benchmarks ranging from general-purpose frameworks to domain-specific assessments, with particular emphasis on the growing importance of multilingual and multimodal evaluation. The analysis reveals that while complete elimination of hallucinations is theoretically impossible in sufficiently complex models, a layered combination of improved architectures, rigorous detection methods, and systemic defenses offers the most effective path toward safe and trustworthy LLM deployment across critical applications.

Cite this paper

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

APA 7

Kumar, S. (2025). Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review. Journal of Information Systems Engineering & Management, 10(60s), 435–443. https://doi.org/10.52783/jisem.v10i60s.13133

MLA 9

Kumar, Sanjay. “Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review.” Journal of Information Systems Engineering & Management, vol. 10, no. 60s, 2025, pp. 435–443. https://doi.org/10.52783/jisem.v10i60s.13133.

Chicago

Kumar, Sanjay. 2025. “Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review.” Journal of Information Systems Engineering & Management 10 (60s): 435–443. https://doi.org/10.52783/jisem.v10i60s.13133.

Harvard

Kumar, S. (2025) ‘Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review’, Journal of Information Systems Engineering & Management, 10(60s), pp. 435–443. doi:10.52783/jisem.v10i60s.13133.

IEEE

S. Kumar, “Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review,” Journal of Information Systems Engineering & Management, vol. 10, no. 60s, pp. 435–443, 2025, doi: 10.52783/jisem.v10i60s.13133.

BibTeX

@article{kumar2025hallucination,
  title     = {{Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review}},
  author    = {Kumar, Sanjay},
  journal   = {Journal of Information Systems Engineering \& Management},
  year      = {2025},
  volume    = {10},
  number    = {60s},
  pages     = {435--443},
  doi       = {10.52783/jisem.v10i60s.13133},
  url       = {https://doi.org/10.52783/jisem.v10i60s.13133}
}

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
  • hallucination mitigation
  • large language models
  • uncertainty estimation
  • retrieval-augmented generation
  • tool integration
  • guardrails
  • human oversight

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?

Kumar, S. (2025). Hallucination Detection and Mitigation in Large Language Models: A Comprehensive Review. Journal of Information Systems Engineering & Management, 10(60s), 435–443. https://doi.org/10.52783/jisem.v10i60s.13133

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 Journal of Information Systems Engineering & Management.

Who wrote this paper?

Sanjay Kumar.

What is the DOI of this paper?

10.52783/jisem.v10i60s.13133. The permanent link is https://doi.org/10.52783/jisem.v10i60s.13133.

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.