Prompts are used to augment labeled data with reasoning chains for supervised fine-tuning (SFT) or in SFT initialization steps before reinforcement learning (RL).

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 (3)

• reinforcement learning concept
• supervised fine-tuning concept
• prompts concept