Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Review

Survey Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models

Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Ting Fu Xinting Huang Enbo Zhao Yulong Chen Longyue Wang A. Lưu Wei Bi Freda Shi Shu-Ming Shi
· 0 citations · 190 references

TL;DR

Taxonomies of the LLM hallucination phenomena and evaluation benchmarks are presented, existing approaches aiming at mitigating LLM hallucination are analyzed, and potential directions for future research are discussed.

Semantic Scholar
View source

Similar papers

How to decrease LLMs’ hallucinations: a proposal

A natural way to decrease hallucinations is every time the authors have new pairs on which to train, they should also again train on the pairs corresponding to well-established facts and rules.

T. Ilina, M. Ceberio, Marcelo F. Frias et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons

This work proposes a five-step diagnostic protocol covering feature correlation, bootstrap stability, sparse versus dense ranking disagreement, intervention baselines, and cross-dataset evaluation as a minimum standard for sparse-neuron localization claims, and investigates prior work using the proposed approach.

Huseyin Cavus, Sebin Sabu, J. Spear et al. · 0 citations
Jun 2026

Indirected Reality

Language, truth, and LLMs How can LLMs appear to know facts about the world when they are trained only on patterns in language rather than direct experience of reality? Hallucinations shouldn’t surprise us. The real mystery is how these systems get anything right at all.

Jim Waldo · 0 citations
#artificial intelligence Preprint Sep 2026

NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass

This work proposes a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset, and transfers the selected neuron identities to train hallucination classifiers on other factual question answering datasets.

Ali Derogar Odolou, Reza Nazari, Mostafa Salehi · 0 citations
#machine learning Preprint Sep 2026

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

It is shown that epistemic uncertainty leaves a measurable trace within intermediate layers, where spikes in attention entropy are associated with reasoning breakdowns, and that attention dispersion is a promising complement to traditional hallucination detection methods.

S. More, Tanuja S. Pawar · 0 citations
#generative ai Review Open access Sep 2026

Systematically Reducing Hallucination in Generative AI from Users to Data to Models

This paper clarifies the above three aspects and how they work together to form a closed-loop hallucination cycle, starting with user feedback as a departure point, moving to the next step of turning error-correction signals into training instances at the data tier, and lastly to internalising the ability of veracity d...

Jun-Hua Chen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.