The mathematical inevitability of hallucinations in Large Language Models is supported by theoretical research on inductive biases (Wu et al., 2024), language identification (Kalavasis et al., 2025), Bayes-optimal estimators (Liu et al., 2025a), and calibration (Kalai and Vempala, 2024; Kalai et al., 2025).

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept