LLaMA 2 (13B) benefits significantly from Chain-of-Thought (CoT) prompting, though ambiguous instructions can lead to hallucinations.

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 (1)

• chain-of-thought concept