🧜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
2025-07-10
SCID: 54.1/ny8q8x2v
Discuss with AI
LLM hallucinationevaluation benchmarkshallucination detectionhallucination mitigationlarge language models
Figures from the paper
Abstract (AI)
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.
Key Findings
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.
Research Object
hallucinations in large language models (LLMs)
Research Subject
the detection, explanation, evaluation, and mitigation of LLM hallucination phenomena
Publication Details
Publication Date
2025-07-10
Journal
Publisher
ISSN
Cited by
2249
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai15
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer2019
LLaMA: Open and Efficient Foundation Language Models2023
A Survey of Large Language Models2026
A Survey on Evaluation of Large Language Models2024
Recurrent neural network based language model2010
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks2020
Training language models to follow instructions with human feedback2022
Lost in the Middle: How Language Models Use Long Contexts2024
Generative Agents: Interactive Simulacra of Human Behavior2023
PaLM: Scaling Language Modeling with Pathways2022
GPT-4 Technical Report2023
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey2023
In-Context Retrieval-Augmented Language Models2023
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model2022
Challenges and Applications of Large Language Models2023
Cited by20
A Survey of Large Language Models2026
Retrieval-Augmented Generation for Large Language Models: A Survey2023
A Survey on Evaluation of Large Language Models2024
A Comprehensive Overview of Large Language Models2025
Unifying Large Language Models and Knowledge Graphs: A Roadmap2024
ChatDev: Communicative Agents for Software Development2024
Explainability for Large Language Models: A Survey2024
Large Language Models for Cyber Security: A Systematic Literature Review2025
Empowering biomedical discovery with AI agents2024
When LLMs meet cybersecurity: a systematic literature review2025
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
Combating misinformation in the age of LLMs: Opportunities and challenges2024
A Survey on Large Language Models for Code Generation2025
Demystifying LLM-Based Software Engineering Agents2025
Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines2025
AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways2025
LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation2025
Large‐Language‐Model‐Based AI Agent for Organic Semiconductor Device Research2024
GenAL: Generative Agent for Adaptive Learning2025
An LLM-based multi-agent system for remote sensing analysis2026