Reference-based metrics are fundamentally limited by their general insensitivity to factual veracity when masked by superficial lexical similarity.

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 (1)

• factual correctness concept