confabulations

Here are 2 public repositories matching this topic...

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

benchmark leaderboard gemini llama language-model claude rag o1 hallucinations ai-evaluation llm gemini-pro llm-benchmarking confabulations deepseek-r1 o3-mini

Driving away from the binary "hallucinations" evals to a more nuanced and context-dependent eval technique.

Add a description, image, and links to the confabulations topic page so that developers can more easily learn about it.

To associate your repository with the confabulations topic, visit your repo's landing page and select "manage topics."