Jul 2026· International Journal on Cybernetics & Informatics· Vol 15, pp. 01-05· 0 citations· 11 references
TL;DR
This paper investigates the structural and methodological sources of hallucination in neural network models, examines three predominant training paradigms, and argues that incomplete training data, flawed train–test partitioning, and the inaccessibility of expert tacit knowledge are root causes of unreliable AI outputs.
Abstract
Contemporary AI language models are increasingly deployed in safety-critical contexts, yet they remain prone to generating dangerous or factually incorrect outputs. Documented examples include AI-generated recipes suggesting the use of chlorine-producing ingredient combinations [1]. Rather than acknowledging these as model errors, developers have characterized them as “hallucinations”—a term that obscures the underlying technical causes. This paper investigates the structural and methodological sources of hallucination in neural network models, examines three predominant training paradigms, and argues that incomplete training data, flawed train–test partitioning, and the inaccessibility of expert tacit knowledge are root causes of unreliable AI outputs. Recommendations for more rigorous training methodologies are proposed.
A concise two-axis framework that integrates an “intrinsic-extrinsic” distinction in source attribution introduced by Ji et al. with a “faithfulness-factuality” distinction in contextual grounding surveyed is presented, yielding four clearly defined hallucination types applicable across tasks, modalities and architectu...
Misbah Khan, Preston Billion-Polak, T. Khoshgoftaar· IEEE Access· 0 citations
A structured survey of AI hallucinations, synthesizing prior research to clarify their evolving definitions, underlying causes, and implications for Information Systems positions AI hallucinations as socio-technical phenomena with direct implications for trust, decision-making, and governance.
This review paper provides a comprehensive overview of hallucinations in GAI and LLMs, and synthesizes a range of correction and mitigation techniques, from proactive measures during training to hybrid approaches that combine detection and intervention.
M. Naser· Language Resources and Evalu...· 0 citations
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
A narrative review distinguishes fabrication, the invention of an entirely non-existent source, from unfaithfulness, the citation of a genuine source in support of a claim it does not contain, and argues that the two failure modes require different detection strategies.
M. Rana, M. Alkhlewi, Turki Abdulaziz Alsohaibani et al.· European Journal of Prosthod...· 0 citations
Generative AI (artificial intelligence) is a leading technology that is multiple sectors like healthcare, finance, education and retail sector. The growth of these sectors is entirely dependent on implementation or adoption of AI based technologies and this adoption will help to make a strong hold a market. LLMs (Large...
Anjali Kaundal, Baljinder Kaur· International Conference Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
