Hallucinations in generative artificial intelligence and large language models: tests, datasets, detection and correction methods

Detecting and Mitigating Hallucinations in Large Language Models: A Comparative Study of Generative and Transformer-Based Approaches

A Review of Hallucination Suppression Technologies for Large Language Models Under RAG Architecture

Large language models (LLMs) suffer inherent factual hallucination defects, which block their deployment in high-risk fields such as medicine and finance. Retrieval-Augmented Generation (RAG) serves a mainstream hallucination mitigation solution by introducing traceable external knowledge evidence. Nevertheless, existing RAG variants are plagued by retrieval noise, poor domain generalization, lack of reasoning verification and inconsistent evaluation standards. This paper adopts classification and comparative analysis as core research methods, and systematically sorts out all hallucination suppression technical routes centered on mitigating LLM hallucinations. Four major categories of anti-hallucination RAG technologies are summarized and their applicable boundaries are compared; two mainstream evaluation benchmarks, CRAG and RAGEval, are thoroughly analyzed. Aggregated experimental results demonstrate that layered stacking of multiple technologies achieves optimal hallucination reduction performance. Finally, this paper summarizes existing research gaps, including lightweight deployment and multimodal expansion, and proposes future research directions for trustworthy RAG systems. This review provides systematic theoretical support for industrial RAG model selection and optimization.

AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models

This work proposes AURORA, a novel hallucination detection framework that shifts the focus from static representations to the weight-gradient dynamics of LLMs, and achieves strong hallucination detection performance across four model families and four benchmark datasets.

A Survey of Hallucinations in Multimodal Large Language Models with Mitigation Strategies

Explainable Hallucination Mitigation in Large Language Models: A Survey

Hallucinations in large language models (LLMs) present major obstacles to reliability in knowledge‐intensive and reasoning‐based tasks. While recent research has explored detection and correction techniques, a unified interpretive framework remains lacking. This survey addresses hallucination mitigation through the lens of explainability, proposing a taxonomy that distinguishes between internal explainability and post hoc explainability. We examine techniques such as attribution tracing, reasoning path construction, and prompt‐based verification, highlighting their roles in transparent diagnosis and structured control. Furthermore, we discuss the constructive role of hallucinations in creative and user‐driven applications, suggesting that context‐aware management may be more effective than blanket suppression. By synthesizing current advances, this review advocates for explainability as a foundation for trustworthy, controllable, and interpretable LLM systems. This article is categorized under: Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Artificial Intelligence Application Areas > Science and Technology

Mitigating Hallucinations in Large Language Models via Retrieval Augmented Generation: A Systematic Review of n8n-Based Implementations

This study systematically examines hallucination phenomena in Large Language Models (LLMs), focusing on their characteristics, causal factors, and mitigation strategies through Retrieval-Augmented Generation (RAG) and low-code orchestration platforms such as n8n. Using a Systematic Literature Review (SLR) approach based on PRISMA 2020 guidelines, this study analysed 40 peer-reviewed articles published between 2020 and 2025 from major scientific databases. The findings reveal that hallucinations are multidimensional, consisting of factual, semantic, and contextual hallucinations influenced by static training data, probabilistic token prediction, prompt ambiguity, and insufficient validation mechanisms. The review further demonstrates that RAG significantly improves factual accuracy by integrating external retrieval systems with LLM generation processes. Recent innovations such as Hybrid Retrieval and GraphRAG enhance contextual relevance and knowledge representation. A major finding of this study is the identification of “Conflict of Information” between external retrieved data and internal LLM knowledge in automated RAG pipelines. Furthermore, this study proposes a novel conceptual framework and taxonomy for hallucination mitigation in low-code AI environments, integrating retrieval, validation, conflict resolution, and workflow orchestration mechanisms. These findings contribute to the development of more reliable, transparent, and scalable AI systems.