Skip to content
#

factual-accuracy

Here are 3 public repositories matching this topic...

Language: All
Filter by language

Dataset of 100 Russian history multiple-choice questions (translated to Latvian) adapted from the Unified State Exam. Includes model evaluation code and results for several LLMs. Designed as a small benchmark to test factual accuracy on Russian history.

  • Updated Nov 22, 2025
  • Jupyter Notebook

Catch AI hallucinations before they catch you. Extract factual claims from LLM outputs, classify them as verified/doubtful/false, and track which models lie the most. Dark & light themes, bulk ops, keyboard shortcuts, full audit trail.

  • Updated Jul 26, 2026
  • Python

Add this topic to your repo

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

Learn more