Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review
Mathematics · 04.03.2025 · 13 (5) · 856
DOI: 10.3390/math13050856 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 04.03.2025. Verfasst von Wan Zhang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 161-mal zitiert (Crossref) und nennt 149 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Retrieval-augmented generation (RAG) leverages the strengths of information retrieval and generative models to enhance the handling of real-time and domain-specific knowledge. Despite its advantages, limitations within RAG components may cause hallucinations, or more precisely termed confabulations in generated outputs, driving extensive research to address these limitations and mitigate hallucinations. This review focuses on hallucination in retrieval-augmented large language models (LLMs). We first examine the causes of hallucinations from different sub-tasks in the retrieval and generation phases. Then, we provide a comprehensive overview of corresponding hallucination mitigation techniques, offering a targeted and complete framework for addressing hallucinations in retrieval-augmented LLMs. We also investigate methods to reduce the impact of hallucination through detection and correction. Finally, we discuss promising future research directions for mitigating hallucinations in retrieval-augmented LLMs.
Förderung
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhang, W., & Zhang, J. (2025). Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review. Mathematics, 13(5), 856. https://doi.org/10.3390/math13050856
Vancouver
Zhang W, Zhang J. Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review. Mathematics. 2025;13(5):856. doi:10.3390/math13050856
BibTeX
@article{Zhang2025,
author = {Zhang, Wan and Zhang, Jing},
title = {Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review},
journal = {Mathematics},
year = {2025},
volume = {13},
number = {5},
pages = {856},
doi = {10.3390/math13050856}
}
EUVIMED