Post-hoc refinement is a mitigation strategy where generated output from a large language model is filtered or corrected using factuality classifiers or auxiliary models.

Authors

• Person: Not available Organization: Frontiers
  Survey and analysis of hallucinations in large language models

Sources

• Survey and analysis of hallucinations in large language models www.frontiersin.org Frontiers via serper

Referenced by nodes (1)

• Large Language Models concept