Semantic Entropy maintains the most consistent performance across both zero-shot and few-shot settings, while traditional metrics like Perplexity and LN-Entropy show higher sensitivity to setting changes.

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)

• Perplexity concept
• semantic entropy concept
• Zero-Shot concept