Preprint · 2025 · Open access

A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation

Seyed Mahmoud Sajjadi Mohammadabadi, Burak Cem Kara, Can Eyüpoğlu, Oktay Karakuş, Mahsa Borhani Peikani

Preprints.org · Published 8 October 2025 · DOI 10.20944/preprints202510.0540.v3

Read the free full textCite this paper

In brief

“A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation” is a 2025 preprint by Seyed Mahmoud Sajjadi Mohammadabadi and 4 co-authors, published in Preprints.org. OpenAlex counts 9 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Preprints.org.

Citations
9
Most cited in
2026 (9)
References
44
Authors
5

Abstract

Despite the strong capabilities of Large Language Models (LLMs) across a wide range of natural language processing tasks, their outputs can still be unreliable. Hallucination is widely used as an umbrella label for several related failures, but its operational meaning varies across tasks and studies. This work provides a comprehensive review of recent advances in understanding, detecting, and mitigating hallucinations in LLMs. We first distinguish hallucination from the separate evaluation dimensions of factuality, faithfulness, and internal consistency. We then introduce an author-proposed organisational taxonomy covering manifestations commonly discussed under hallucination, including factual contradictions, context conflicts, fabrication, self-contradiction, and emerging failures in reasoning traces and agentic trajectories. We review detection methods based on level of access to the model, ranging from white-box approaches to grey-box uncertainty estimation and black-box consistency and verification methods. We further organize these approaches according to the signals they exploit, including uncertainty, semantic consistency, external evidence, and internal representations, and discuss their strengths and limitations across different deployment settings. Finally, we survey mitigation strategies across the LLM lifecycle, including (1) data-centric approaches such as data curation and retrieval-augmented pre-training, (2) model-centric approaches such as supervised fine-tuning, preference optimization, abstention-aware reinforcement learning, and knowledge editing, and (3) inference-time approaches such as retrieval-augmented generation, self-verification, and decoding or activation-level interventions. Rather than viewing these strategies as isolated solutions, we argue that reliable hallucination mitigation requires complementary controls across multiple stages of the model lifecycle. Key challenges include scalable and provenance-aware data curation, the alignment–capability trade-off, reliable composition of mitigation techniques, and the need to evaluate and modify reasoning and agentic processes rather than only isolated factual associations.

Cite this paper

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

APA 7

Mohammadabadi, S. M. S., Kara, B. C., Eyüpoğlu, C., Karakuş, O., & Peikani, M. B. (2025). A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation. Preprints.org. https://doi.org/10.20944/preprints202510.0540.v3

MLA 9

Mohammadabadi, Seyed Mahmoud Sajjadi, et al. “A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation.” Preprints.org, 2025. https://doi.org/10.20944/preprints202510.0540.v3.

Chicago

Mohammadabadi, Seyed Mahmoud Sajjadi, Burak Cem Kara, Can Eyüpoğlu, Oktay Karakuş, and Mahsa Borhani Peikani. 2025. “A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation.” Preprints.org. https://doi.org/10.20944/preprints202510.0540.v3.

Harvard

Mohammadabadi, S. M. S. et al. (2025) ‘A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation’, Preprints.org. doi:10.20944/preprints202510.0540.v3.

IEEE

S. M. S. Mohammadabadi, B. C. Kara, C. Eyüpoğlu, O. Karakuş, and M. B. Peikani, “A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation,” Preprints.org, 2025, doi: 10.20944/preprints202510.0540.v3.

BibTeX

@misc{mohammadabadi2025survey,
  title     = {{A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation}},
  author    = {Mohammadabadi, Seyed Mahmoud Sajjadi and Kara, Burak Cem and Eyüpoğlu, Can and Karakuş, Oktay and Peikani, Mahsa Borhani},
  howpublished = {Preprints.org},
  year      = {2025},
  doi       = {10.20944/preprints202510.0540.v3},
  url       = {https://doi.org/10.20944/preprints202510.0540.v3}
}

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

  • hallucinations
  • large language models
  • hallucination detection
  • hallucination mitigation
  • factuality
  • faithfulness
  • internal consistency
  • self-contradiction

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?

Mohammadabadi, S. M. S., Kara, B. C., Eyüpoğlu, C., Karakuş, O., & Peikani, M. B. (2025). A Survey on Hallucination in Large Language Models: Definitions, Detection, and Mitigation. Preprints.org. https://doi.org/10.20944/preprints202510.0540.v3

How many times has this paper been cited?

9 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 Preprints.org.

Who wrote this paper?

Seyed Mahmoud Sajjadi Mohammadabadi, Burak Cem Kara, Can Eyüpoğlu, Oktay Karakuş, Mahsa Borhani Peikani.

What is the DOI of this paper?

10.20944/preprints202510.0540.v3. The permanent link is https://doi.org/10.20944/preprints202510.0540.v3.

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.