The authors of the study did not evaluate larger closed-source models like Anthropic's Claude or OpenAI's GPT-4, noting that these systems have undergone extensive fine-tuning and may exhibit different hallucination profiles compared to the models tested.

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 (3)

• OpenAI entity
• Claude concept
• Anthropic entity