The 'Semantic Density' method provides response-wise confidence and uncertainty scores for detecting Large Language Model hallucinations by extracting information from a probability distribution perspective in semantic space, functioning as an 'off-the-shelf' tool for various task types. This method uses AUROC and AUPR metrics and is evaluated on the CoQA, TriviaQA, SciQ, and NQ 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 (1)

• TriviaQA concept