mlsanityData to 7 Oct 2026

Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention

arXiv 2608.26168 ↗First posted 20 Jul 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The lifecycle of hallucination in LLMs is a concept that enables building solid frameworks on the control and reliability of LLMs in high-stakes environments, including health, legal, and scientific research. Although previous surveys have primarily focused on detection or mitigation, this survey provides a lifecycle-based overview of the hallucinations in the LLMs, their cause, detection, mitigation, and prevention.We propose a three-fold categorization of hallucinations across the LLM lifecycle: data-related, training-related, and inference-related, which is consistent with the lifecycle of the development of the LLM. Each of these stages is discussed regarding the cause of hallucinations, their detection, and the ways they can be addressed under specific mitigation or prevention interventions. In addition, we discuss the available benchmark data using a number of parameters so as to establish their suitability in identifying, restricting and managing hallucinations. The survey provides researchers and practitioners with a standardized framework to understand, diagnose, and cure hallucinations in a systematic system to present actionable data to build safer and more reliable LLMs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 118 of its 147 references that are in the map. First posted on arXiv 20 Jul 2026.

Builds on

118 of 147 references.

References · 118

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2017Deep reinforcement learning from human preferencescited by 3,846
  10. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  11. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  12. 2019The Curious Case of Neural Text Degenerationcited by 2,881
38 more
  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  3. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  4. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  5. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  6. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  7. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  8. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  9. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  10. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  11. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  12. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  13. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  14. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  15. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  16. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  17. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  18. 2023Textbooks Are All You Needcited by 561
  19. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  20. 2022Memory-Based Model Editing at Scalecited by 443
  21. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  22. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  23. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 367
  24. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  25. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  26. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  27. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  28. 2023How Language Model Hallucinations Can Snowballcited by 310
  29. 2020Calibration of Pre-trained Transformerscited by 307
  30. 2023SemDeDup: Data-efficient learning at web-scale through semantic deduplicationcited by 295
  31. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  32. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  33. 2024Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?cited by 227
  34. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 223
  35. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  36. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  37. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  38. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159

50 most cited of 118 All 118 (JSON)

Built on by

Not cited yet.