lechmazur/confabulations
Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.
17 best points · 3 comments · 2 Hacker News posts · 251 GitHub stars · View on GitHub
Hacker News discussions
- LLM Hallucination Benchmark: R1, o1, o3-mini, Gemini 2.0 Flash Think Exp 01-21 (17 points, 3 comments, by zone411, 2025-02-10)
- LLM Confabulation (Hallucination) Leaderboard (6 points, 0 comments, by zone411, 2024-10-10)