Wang, Cunxiang, Xiaoze Liu, Yuanhao Yue, et al. 2026. “Survey on Factuality in Large Language Models.” ACM Computing Surveys 58 (1): 1–37. https://doi.org/10.1145/3742420.

Notes

• “Factuality refers to the ability of an LLM to provide information that is accurate, verifiable, and aligned with real-world knowledge.” (Wang et al., 2026, p. 4)
• Related issues
  • Factuality
  • Hallucinations
  • Outdated Information
  • Domain-specificity
• Causes of Factual Errors
  • Model-level causes
    • Domain Knowledge Deficit
    • Outdated Information
    • Immemorization
    • Forgetting
    • Reasoning Failure
  • Retrieval-level Causes
    • Insufficient Information
    • Misinformation Not Recognized by LLMs
    • Distracting Information
    • Misinterpretation of Related Information
  • Inference-level Causes
    • Snowballing
    • Erroneous Decoding
    • Exposure Bias

In-text annotations