Analyzing the embedding space of large language model outputs by measuring the Minkowski distance between embedded keywords in genuine versus hallucinated answers allows for hallucination detection with approximately 66% accuracy without external fact-checking.

Authors

• Person: Not available Organization: GitHub
  EdinburghNLP/awesome-hallucination-detection - GitHub

Sources

• EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub via serper

Referenced by nodes (1)

• hallucination detection concept