The authors of 'Re-evaluating Hallucination Detection in LLMs' argue that ROUGE is a poor proxy for human judgment in evaluating hallucination detection because its design for lexical overlap does not inherently capture factual correctness.

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 (3)

• factual correctness concept
• hallucination detection concept
• ROUGE concept