A Survey of Hallucination in Large Foundation Models

2023/09/12 by Vipula Rawte, Amit Sheth, Rawte, Vipula +3 · 48 citations
Economics, Econometrics and Finance · Neuroscience · Psychology · #Artificial Intelligence (cs.AI) #Complex Systems and Time Series Analysis #Computation and Language (cs.CL) #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Information Retrieval (cs.IR) #Mental Health Research Topics

paper · pdf · doi:10.48550/arxiv.2309.05922

openalex publication_date 2023/09/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Hallucination in a foundation model (FM) refers to the generation of content that strays from factual reality or includes fabricated information. This survey paper provides an extensive overview of recent efforts that aim to identify, elucidate, and tackle the problem of hallucination, with a particular focus on ``Large'' Foundation Models (LFMs). The paper classifies various types of hallucination phenomena that are specific to LFMs and establishes evaluation criteria for assessing the extent of hallucination. It also examines existing strategies for mitigating hallucination in LFMs and discusses potential directions for future research in this area. Essentially, the paper offers a comprehensive examination of the challenges and solutions related to hallucination in LFMs.

Cited by

• FaithLens: Detecting and Explaining Faithfulness Hallucination
• Multi-Agent LLM Committees for Autonomous Software Beta Testing
• Mitigating Hallucinations in Healthcare LLMs with Granular Fact-Checking and Domain-Specific Adaptation
• Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
• MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
• A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem
• Can LLMs Make (Personalized) Access Control Decisions?
• Enhancing Sequential Recommendation with World Knowledge from Large Language Models
• Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models
• Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
• A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI
• Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning
• What Limits Agentic Systems Efficiency?
• Spurious reconstruction from brain activity
• MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
• A Survey on Evaluation of Large Language Models
• Reallocating Attention Across Layers to Reduce Multimodal Hallucination
• Domain-Grounded Evaluation of LLMs in International Student Knowledge
• TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
• Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching
• Navigating the AI era: university communication strategies and perspectives on generative AI tools
• Advances in Large Language Models for Medicine
• The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs
• A funny companion: Distinct neural responses to AI- versus human-attributed humor
• MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems
• A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
• AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs
• Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
• Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering
• Can we Evaluate RAGs with Synthetic Data?
• SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs
• CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
• GOFAI meets Generative AI: Development of Expert Systems by means of Large Language Models
• SCALEFeedback: A Large-Scale Dataset of Synthetic Computer Science Assignments for LLM-generated Educational Feedback Research
• Dean of LLM Tutors: Exploring Comprehensive and Automated Evaluation of LLM-generated Educational Feedback via LLM Feedback Evaluators
• Towards Reliable Generative AI-Driven Scaffolding: Reducing Hallucinations and Enhancing Quality in Self-Regulated Learning Support
• Adapting Vision-Language Models Without Labels: A Comprehensive Survey
• A Survey on AgentOps: Categorization, Challenges, and Future Directions
• MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
• Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning
• Extracting Visual Facts from Intermediate Layers for Mitigating Hallucinations in Multimodal Large Language Models
• Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration
• First Hallucination Tokens Are Different from Conditional Ones
• Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models
• Mitigating Object Hallucinations via Sentence-Level Early Intervention
• Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding
• Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation

Related

• A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models
• The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations
• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare