For the Llama model, the performance discrepancy between ROUGE and LLM-as-Judge evaluation narrows significantly when using few-shot examples compared to zero-shot settings.

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)

• Zero-Shot concept
• ROUGE concept
• LLM-as-a-judge concept