ROUGE, a metric based on lexical overlap, exhibits high recall but extremely low precision when used for hallucination detection, leading to misleading performance estimates.

Authors

• Person: Not available Organization: arXiv
  The Illusion of Progress: Re-evaluating Hallucination Detection in ...

Sources

• The Illusion of Progress: Re-evaluating Hallucination Detection in ... arxiv.org arXiv via serper

Referenced by nodes (2)

• hallucination detection concept
• ROUGE concept