mlsanityData to 7 Oct 2026

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models

arXiv 2401.03205 ↗First posted 6 Jan 2024cs.CLcited by 87

Not on the map. Why?

Abstract (arXiv)

In the era of large language models (LLMs), hallucination (i.e., the tendency to generate factually incorrect content) poses great challenge to trustworthy and reliable deployment of LLMs in real-world applications. To tackle the LLM hallucination, three key questions should be well studied: how to detect hallucinations (detection), why do LLMs hallucinate (source), and what can be done to mitigate them (mitigation). To address these challenges, this work presents a systematic empirical study on LLM hallucination, focused on the the three aspects of hallucination detection, source and mitigation. Specially, we construct a new hallucination benchmark HaluEval 2.0, and designs a simple yet effective detection method for LLM hallucination. Furthermore, we zoom into the different training or utilization stages of LLMs and extensively analyze the potential factors that lead to the LLM hallucination. Finally, we implement and examine a series of widely used techniques to mitigate the hallucinations in LLMs. Our work has led to several important findings to understand the hallucination origin and mitigate the hallucinations in LLMs. Our code and data can be accessed at https://github.com/RUCAIBox/HaluEval-2.0.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 6 Jan 2024.

Builds on

39 of 61 references.

References · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  11. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  12. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
27 more
  1. 2022Galactica: A Large Language Model for Sciencecited by 736
  2. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  3. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  4. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  5. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  6. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  7. 2023How Language Model Hallucinations Can Snowballcited by 310
  8. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  9. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  10. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  11. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  12. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  13. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  14. 2023Do Language Models Know When They're Hallucinating References?cited by 115
  15. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  16. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  17. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  18. 2023Towards Mitigating Hallucination in Large Language Models via Self-Reflectioncited by 81
  19. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 67
  20. 2023Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Modelscited by 67
  21. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 55
  22. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  23. 2023TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Taskscited by 48
  24. 2022How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysiscited by 42
  25. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32
  26. 2023The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Whocited by 19
  27. 2023Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concretenesscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 25; 2025: 39; 2026: 23.

87 papers.

Sort:

By area:

  1. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 146
  2. 2025HalluLens: LLM Hallucination Benchmarkcited by 88
  3. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  4. 2024PhD: A ChatGPT-Prompted Visual hallucination Evaluation Datasetcited by 44
  5. 2024Detecting Hallucinations in Large Language Model Generation: A Token Probability Approachcited by 40
  6. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
  7. 2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoningcited by 33
  8. 2024Content Moderation by LLM: From Accuracy to Legitimacycited by 30
  9. 2024HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluationcited by 26
  10. 2024DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinationscited by 23
  11. 2024Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Modelscited by 21
  12. 2024OLAPH: Improving Factuality in Biomedical Long-form Question Answeringcited by 20
38 more
  1. 2024Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Surveycited by 19
  2. 2024Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulnesscited by 17
  3. 2025Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoningcited by 17
  4. 2025MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Themcited by 16
  5. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 15
  6. 2024Pensieve: Retrospect-then-Compare Mitigates Visual Hallucinationcited by 14
  7. 2024Distinguishing Ignorance from Error in LLM Hallucinationscited by 14
  8. 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learningcited by 14
  9. 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenescited by 13
  10. 2024Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinationscited by 12
  11. 2024CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularitycited by 12
  12. 2024FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMscited by 11
  13. 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
  14. 2025Uncertainty-Aware Decoding with Minimum Bayes Riskcited by 10
  15. 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinationscited by 9
  16. 2025HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMscited by 8
  17. 2025An Empirical Study on Prompt Compression for Large Language Modelscited by 8
  18. 2024DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluationcited by 6
  19. 2024CiteBART: Learning to Generate Citations for Local Citation Recommendationcited by 6
  20. 2025When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retractioncited by 6
  21. 2025Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Modelscited by 6
  22. 2025Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Promptingcited by 6
  23. 2025ZINA: Multimodal Fine-grained Hallucination Detection and Editingcited by 5
  24. 2025Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinationscited by 5
  25. 2026Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levelscited by 5
  26. 2024DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicinecited by 4
  27. 2025aiXamine: Simplified LLM Safety and Securitycited by 4
  28. 2025First Hallucination Tokens Are Different from Conditional Onescited by 4
  29. 2025LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signalscited by 4
  30. 2026Investigating Social Bias Changes in Quantized Language Modelscited by 4
  31. 2026Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematicscited by 4
  32. 2025HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Modelscited by 3
  33. 2026Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrievalcited by 3
  34. 2026Halluverse-M^3: A multitask multilingual benchmark for hallucination in LLMscited by 3
  35. 2026The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agentscited by 3
  36. 2026Automatic Layer Selection for Hallucination Detectioncited by 3
  37. 2024Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Trainingcited by 2
  38. 2024Self-Explained Keywords Empower Large Language Models for Code Generationcited by 2

50 most cited of 87 All 87 (JSON)