The RefChecker benchmark dataset sources its examples from three specific datasets: NaturalQuestions (development set) for zero context closed-book QA, MS MARCO (development set) for noisy context retrieval-augmented generation, and databricks-dolly-15k for accurate context summarization, closed QA, and information extraction.

Authors

• Person: Not available Organization: Amazon Science
  New tool, dataset help detect hallucinations in large language models

Sources

• New tool, dataset help detect hallucinations in large language models www.amazon.science Amazon Science via serper

Referenced by nodes (3)

• Retrieval-Augmented Generation (RAG) concept
• RefChecker concept
• NaturalQuestions concept