GPT-4 avoids factual hallucinations on the TruthfulQA benchmark by using nuanced, cautious phrasing, a strategy likely derived from reinforcement learning from human feedback.

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)

• TruthfulQA concept
• Reinforcement learning from human feedback (RLHF) concept