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

🧜Песнь сирены в океане ИИ: обзор галлюцинаций в больших языковых моделях
Yue Zhang, Yu Zhang, Longyue Wang, Deng Cai, Yafu Li, Leyang Cui, Xinting Huang, Lemao Liu, Tingchen Fu, Yulong Chen, Anh Tuan Luu, Freda Shi, Wei Bi, Enbo Zhao, Shuming Shi
2025-07-10

LLM hallucinationevaluation benchmarkshallucination detectionhallucination mitigationlarge language models
Abstract While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this article, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
1
Existing research on hallucination detection, explanation, and mitigation is reviewed, emphasizing challenges specific to LLMs.
2
Hallucinations pose a substantial reliability challenge for deploying LLMs in real-world scenarios.
3
Large language models can generate content that diverges from user input, contradicts prior context, or conflicts with established world knowledge.
4
The paper identifies potential future research directions for improving understanding and reducing LLM hallucinations.
5
The survey organizes LLM hallucinations into taxonomies covering their phenomena and evaluation benchmarks.

hallucinations in large language models (LLMs)

the detection, explanation, evaluation, and mitigation of LLM hallucination phenomena

Publication Details
Publication Date
2025-07-10
Journal
Publisher
ISSN
Cited by
2249
Access Type
Author Information
Authors
Yue Zhang
Yu Zhang
Longyue Wang
Deng Cai
Yafu Li
Leyang Cui
Xinting Huang
Lemao Liu
Tingchen Fu
Yulong Chen
Anh Tuan Luu
Freda Shi
Wei Bi
Enbo Zhao
Shuming Shi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%