A research work on hallucination detection provides a connection between test instances and training support sets, allows for controlling epistemic uncertainty, and precedes sparse auto-encoder (SAE) and contrastive-representation-based interpretability methods.

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