Journal article · 2025 · Open access

From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs

Ioannis Kazlaris, Efstathios N. Antoniou, Konstantinos Diamantaras, Charalampos Bratsas

AI, 6(10), 260 · Published 3 October 2025 · DOI 10.3390/ai6100260

Free PDFView at the publisherCite this paper

In brief

“From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs” is a 2025 journal article by Ioannis Kazlaris and 3 co-authors, published in AI. OpenAlex counts 24 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 AI.

Citations
24
Most cited in
2026 (20)
Field-weighted impact
5.86
References
323
Authors
4

Abstract

Large Language Models (LLMs) exhibit remarkable generative capabilities but remain vulnerable to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or inconsistent with source material. To address the lack of methodologically grounded surveys, this paper introduces a novel method-oriented taxonomy of hallucination mitigation strategies in text-based LLMs. The taxonomy organizes over 300 studies into six principled categories: Training and Learning Approaches, Architectural Modifications, Input/Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. Beyond mapping the field, we identify persistent challenges such as the absence of standardized evaluation benchmarks, attribution difficulties in multi-method systems, and the fragility of retrieval-based methods when sources are noisy or outdated. We also highlight emerging directions, including knowledge-grounded fine-tuning and hybrid retrieval–generation pipelines integrated with self-reflective reasoning agents. This taxonomy provides a methodological framework for advancing reliable, context-sensitive LLM deployment in high-stakes domains such as healthcare, law, and defense.

Cite this paper

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

APA 7

Kazlaris, I., Antoniou, E. N., Diamantaras, K., & Bratsas, C. (2025). From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs. AI, 6(10), 260. https://doi.org/10.3390/ai6100260

MLA 9

Kazlaris, Ioannis, et al. “From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs.” AI, vol. 6, no. 10, 2025, p. 260. https://doi.org/10.3390/ai6100260.

Chicago

Kazlaris, Ioannis, Efstathios N. Antoniou, Konstantinos Diamantaras, and Charalampos Bratsas. 2025. “From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs.” AI 6 (10): 260. https://doi.org/10.3390/ai6100260.

Harvard

Kazlaris, I. et al. (2025) ‘From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs’, AI, 6(10), p. 260. doi:10.3390/ai6100260.

IEEE

I. Kazlaris, E. N. Antoniou, K. Diamantaras, and C. Bratsas, “From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs,” AI, vol. 6, no. 10, p. 260, 2025, doi: 10.3390/ai6100260.

BibTeX

@article{kazlaris2025from,
  title     = {{From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs}},
  author    = {Kazlaris, Ioannis and Antoniou, Efstathios N. and Diamantaras, Konstantinos and Bratsas, Charalampos},
  journal   = {AI},
  year      = {2025},
  volume    = {6},
  number    = {10},
  pages     = {260},
  doi       = {10.3390/ai6100260},
  url       = {https://doi.org/10.3390/ai6100260}
}

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 taxonomy
  • training methods
  • architectural alterations
  • prompt optimization
  • interpretability
  • diagnostic methods

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?

Kazlaris, I., Antoniou, E. N., Diamantaras, K., & Bratsas, C. (2025). From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs. AI, 6(10), 260. https://doi.org/10.3390/ai6100260

How many times has this paper been cited?

24 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 AI.

Who wrote this paper?

Ioannis Kazlaris, Efstathios N. Antoniou, Konstantinos Diamantaras, Charalampos Bratsas.

What is the DOI of this paper?

10.3390/ai6100260. The permanent link is https://doi.org/10.3390/ai6100260.

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.