vidconcept-sum generates structured, factual summaries of scientific/educational concepts from video titles or descriptions using an LLM.
-
Updated
Dec 21, 2025 - Python
vidconcept-sum generates structured, factual summaries of scientific/educational concepts from video titles or descriptions using an LLM.
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.
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.
To associate your repository with the factual-accuracy topic, visit your repo's landing page and select "manage topics."