The repetition_penalty parameter penalizes tokens that appeared earlier in the sequence, which can prevent repetitive loops but may also discourage large language models from correctly reusing technical terms.

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