The Vectara hallucination leaderboard explicitly filters out model responses that refuse to summarize a document or provide one-to-two word answers to prevent models from gaming the evaluation.

Authors

• Person: Not available Organization: Vectara
  vectara/hallucination-leaderboard - GitHub

Sources

• vectara/hallucination-leaderboard - GitHub github.com Vectara via serper

Referenced by nodes (2)

• summarization concept
• Vectara LLM Hallucination Leaderboard concept