Siren's Song in the AI Ocean: A Survey on Hallucination in Large 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 paper, 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.

work in progress;

Cited by in corpus (23)

• Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
• Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
• Factuality Challenges in the Era of Large Language Models
• Tool Learning with Large Language Models: A Survey
• The effect of source disclosure on evaluation of AI-generated messages: A two-part study
• Exploring the psychology of LLMs' Moral and Legal Reasoning
• AppPoet: Large Language Model based Android malware detection via multi-view prompt engineering
• A Survey on Symbolic Knowledge Distillation of Large Language Models
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
• Large language models as oracles for instantiating ontologies with domain-specific knowledge
• Automated Review Generation Method Based on Large Language Models
• Towards Reliable Generative AI-Driven Scaffolding: Reducing Hallucinations and Enhancing Quality in Self-Regulated Learning Support
• KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration
• Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models
• A Scoping Review of Natural Language Processing in Addressing Medically Inaccurate Information: Errors, Misinformation, and Hallucination
• Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets
• A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models
• Analyzing Multimodal Interaction Strategies for LLM-Assisted Manipulation of 3D Scenes
• Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning
• InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions
• RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
• Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory