Datadog classifies disagreements between an LLM-generated answer and the provided context into two types: contradictions, which are claims that go directly against the context, and unsupported claims, which are parts of the answer not grounded in the context.

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 (2)

• Datadog entity
• context concept