Chain-of-Thought prompting can backfire by making hallucinations more elaborate if a model fundamentally lacks knowledge on a query, as the model may rationalize a falsehood in detail.

Authors

• Person: Not available Organization: Frontiers
  Survey and analysis of hallucinations in large language models

Sources

• Survey and analysis of hallucinations in large language models www.frontiersin.org Frontiers via serper

Referenced by nodes (2)

• hallucination concept
• chain-of-thought concept