From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs
Preprint
- 27 August 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Large Language Models (LLMs) exhibit remarkable generative capabilities but remain susceptible to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or in-consistent with source material. This paper presents a method-oriented taxonomy of hallucination mitigation strategies in text-based Large Language Models (LLMs), encompassing six categories: Training and Learning Approaches, Architectural Modifications, Input / Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. By synthesizing over 300 studies, we identify persistent challenges including the lack of standardized evaluation benchmarks, attribution difficulties in multi-method frameworks, computational trade-offs between accuracy and latency, and the vulnerability of retrieval-based methods to noisy or outdated sources. We highlight underexplored research directions such as knowledge-grounded fine-tuning strategies balancing factuality with creative utility; and hybrid retrieval–generation pipelines integrated with self-reflective reasoning agents. This taxonomy offers both a synthesis of current knowledge and a roadmap for advancing reliable, con-text-sensitive mitigation in high-stakes domains such as healthcare, law, and defense.Keywords
All Related Versions
- Version 1, 2025-08-27, Preprints
- Published version: AI, 6 (10), 260.
This publication has 187 references indexed in Scilit:
- LLMs Will Always Hallucinate, and We Need to Live with This2025
- WITHDRAWN: Ambiguity processing in Large Language Models: Detection, resolution, and the path to hallucinationNatural Language Processing Journal, 2025
- AggTruth: Contextual Hallucination Detection Using Aggregated Attention Scores in LLMs2025
- Reducing hallucinations of large language models via hierarchical semantic pieceComplex & Intelligent Systems, 2025
- Retrieval In Decoder benefits generative models for explainable complex question answeringNeural Networks, 2024
- Enhancing Reliability in Large Language Models: Self-Detection of Hallucinations With Spontaneous Self-Checks2024
- Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language modelsArtificial Intelligence Review, 2024
- Accuracy, Consistency, and Hallucination of Large Language Models When Analyzing Unstructured Clinical Notes in Electronic Medical RecordsJAMA Network Open, 2024
- Still no lie detector for language models: probing empirical and conceptual roadblocksPhilosophical Studies, 2024
- BLEU2001