The 'Kernel Language Entropy' method evaluates semantic uncertainty in Large Language Model responses by generating multiple response samples, measuring their semantic similarity as a density matrix (semantic kernel), and quantifying uncertainty using the von Neumann entropy of that matrix to detect and mitigate hallucinations. This method uses AUROC and AURAC metrics and is evaluated on the TriviaQA, SQuAD, BioASQ, NQ, and SVAMP datasets.

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 (2)

• TriviaQA concept
• SQuAD concept