mlsanityData to 14 Oct 2026

Cognitive Mirage: A Review of Hallucinations in Large Language Models

arXiv 2309.06794 ↗First posted 13 Sep 2023cs.CL cs.AI cs.LGcited by 84

Not on the map. Why?

Abstract (arXiv)

As large language models continue to develop in the field of AI, text generation systems are susceptible to a worrisome phenomenon known as hallucination. In this study, we summarize recent compelling insights into hallucinations in LLMs. We present a novel taxonomy of hallucinations from various text generation tasks, thus provide theoretical insights, detection methods and improvement approaches. Based on this, future research directions are proposed. Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future. As hallucinations garner significant attention from the community, we will maintain updates on relevant research progress.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Builds on 149 of its 184 references that are in the map. First posted on arXiv 13 Sep 2023.

Builds on

149 of 184 references.

References · 149

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  10. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  12. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
38 more
  1. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  5. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2020Learning to summarize from human feedbackcited by 2,588
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  11. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  13. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  14. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  15. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  16. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  17. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  18. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  19. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  20. 2022Editing Models with Task Arithmeticcited by 1,120
  21. 2023LIMA: Less Is More for Alignmentcited by 1,100
  22. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  23. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  24. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  25. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  26. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  27. 2023A Survey on Multimodal Large Language Modelscited by 909
  28. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  29. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  30. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  31. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  32. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  33. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  34. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 722
  35. 2022PAL: Program-aided Language Modelscited by 652
  36. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  37. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  38. 2023Active Retrieval Augmented Generationcited by 516

50 most cited of 149 All 149 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 40; 2025: 20; 2026: 13.

84 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  2. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  3. 2024Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judgescited by 205
  4. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  5. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
  6. 2024LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigationcited by 93
  7. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 91
  8. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 86
  9. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  10. 2024Financial Report Chunking for Effective Retrieval Augmented Generationcited by 46
  11. 2024Multicalibration for Confidence Scoring in LLMscited by 46
  12. 2024A Survey on Large Language Model Hallucination via a Creativity Perspectivecited by 38
38 more
  1. 2024THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Modelscited by 36
  2. 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
  3. 2025CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuningcited by 31
  4. 2024Source-Aware Training Enables Knowledge Attribution in Language Modelscited by 30
  5. 2023FactCHD: Benchmarking Fact-Conflicting Hallucination Detectioncited by 29
  6. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  7. 2024Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Modelscited by 25
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  9. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 23
  10. 2024Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecuritycited by 21
  11. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  12. 2024Defining and Detecting the Defects of the Large Language Model-based Autonomous Agentscited by 16
  13. 2024AutoSAT: Automatically Optimize SAT Solvers via Large Language Modelscited by 15
  14. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  15. 2024Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Modelscited by 12
  16. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generationcited by 12
  17. 2023Measurement in the Age of LLMs: An Application to Ideological Scalingcited by 11
  18. 2024Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answeringcited by 11
  19. 2024MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Datasetcited by 11
  20. 2024FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMscited by 11
  21. 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Biascited by 11
  22. 2025Uncertainty-Aware Decoding with Minimum Bayes Riskcited by 11
  23. 2024Automated Text Scoring in the Age of Generative AI for the GPU-poorcited by 10
  24. 2023The Confidence-Competence Gap in Large Language Models: A Cognitive Studycited by 9
  25. 2024ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Modelscited by 9
  26. 2025Unified Multimodal Understanding via Byte-Pair Visual Encodingcited by 9
  27. 2024Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answeringcited by 8
  28. 2024Blockchain for Large Language Model Security and Safety: A Holistic Surveycited by 8
  29. 2024Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistrycited by 8
  30. 2025Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineeringcited by 8
  31. 2024The Effects of Hallucinations in Synthetic Training Data for Relation Extractioncited by 7
  32. 2023Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Constructioncited by 6
  33. 2024DAWN: Designing Distributed Agents in a Worldwide Networkcited by 6
  34. 2025Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generationcited by 6
  35. 2024Mechanistic interpretability of large language models with applications to the financial services industrycited by 5
  36. 2025Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECKcited by 5
  37. 2023Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervisioncited by 4
  38. 2024Large Language Models Meet User Interfaces: The Case of Provisioning Feedbackcited by 4

50 most cited of 84 All 84 (JSON)