ROUGE and other commonly used metrics based on n-grams and semantic similarity share vulnerabilities in hallucination detection tasks, indicating a broader deficiency in current evaluation practices.

Authors

• Person: Not available Organization: arXiv
  Re-evaluating Hallucination Detection in LLMs - arXiv

Sources

• Re-evaluating Hallucination Detection in LLMs - arXiv arxiv.org arXiv via serper

Referenced by nodes (2)

• hallucination detection concept
• ROUGE concept