Large Language Models generate answers based on the statistical plausibility of the answer's form rather than its content because training data contains millions of question-answer pairs that create strong associations between question formats and expected answer types.

Authors

• Person: M. Brenndoerfer Organization: mbrenndoerfer.com
  Hallucination Causes: Why Language Models Fabricate Facts

Sources

• Hallucination Causes: Why Language Models Fabricate Facts mbrenndoerfer.com M. Brenndoerfer · mbrenndoerfer.com via serper

Referenced by nodes (1)

• Large Language Models concept