The Datadog hallucination detection method showed the smallest drop in F1 scores between HaluBench and RAGTruth, suggesting robustness as hallucinations become harder to detect.

Authors

• Person: Aritra Biswas, Noé Vernier Organization: Datadog
  Detecting hallucinations with LLM-as-a-judge: Prompt ... - Datadog

Sources

• Detecting hallucinations with LLM-as-a-judge: Prompt ... - Datadog www.datadoghq.com Aritra Biswas, Noé Vernier · Datadog via serper

Referenced by nodes (4)

• hallucination detection concept
• Datadog entity
• F1 score concept
• RAGTruth concept