Large Language Models (LLMs) can be constrained to specific output formats by combining the Finite State Machine's (FSM) list of valid tokens with the model's probability distribution and setting the logprob or logit of invalid tokens to negative infinity.

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)

• Large Language Models concept
• probability distribution concept