OpenAI research suggests that large language models hallucinate because they are rewarded for guessing an answer even when they are uncertain, rather than being trained to state 'I don't know.'

Authors

• Person: Not available Organization: AI Innovations and Insights
  What Really Causes Hallucinations in LLMs? - AI Exploration Journey

Sources

• What Really Causes Hallucinations in LLMs? - AI Exploration Journey aiexpjourney.substack.com AI Innovations and Insights via serper

Referenced by nodes (2)

• Large Language Models concept
• OpenAI entity