Post-training methods like Reinforcement Learning from Human Feedback (RLHF) contribute to LLM hallucinations by using binary scoring systems that punish models for saying 'I don't know,' which incentivizes confident guessing.

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)

• LLM hallucinations in medicine concept
• Reinforcement learning from human feedback (RLHF) concept