Hallucinations can be categorized into four attribution types based on Prompt Sensitivity (PS) and Model Variation (MV) scores: Prompt-dominant (high PS, low MV), Model-dominant (low PS, high MV), Mixed-origin (high PS, high MV), and Unclassified/noise (low PS, low MV).

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
• Prompt Sensitivity concept