LLM-based evaluation, particularly using GPT-4, yields the best overall results for detecting hallucinations in language models.

Authors

• Person: Not available Organization: arXiv
  Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection

Sources

• Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection arxiv.org arXiv via serper

Referenced by nodes (1)

• Language Model concept