@kyutai_labs: KairosQA contains over 7000 temporally grounded questions created using Wikidata. We look for questions whose answers c…

X AI KOLs Following Papers

Summary

Kyutai Labs introduces KairosQA, a dataset of over 7,000 temporally grounded questions from Wikidata, focusing on popular Wikipedia pages where answers changed multiple times between 2018 and 2025.

KairosQA contains over 7000 temporally grounded questions created using Wikidata. We look for questions whose answers changed at least twice between 2018 and 2025, and filter to only popular Wikipedia pages. https://t.co/kFiJKM3MRT
Original Article
View Cached Full Text

Cached at: 05/27/26, 07:03 AM

KairosQA contains over 7000 temporally grounded questions created using Wikidata. We look for questions whose answers changed at least twice between 2018 and 2025, and filter to only popular Wikipedia pages. https://t.co/kFiJKM3MRT

Similar Articles

Introducing SimpleQA

OpenAI Blog

OpenAI introduces SimpleQA, a new factuality benchmark dataset with 4,326 short fact-seeking questions designed to evaluate frontier language models on their ability to provide accurate answers without hallucination. The dataset achieves high quality through dual independent annotation, rigorous criteria, and achieves only ~3% estimated error rate, with GPT-4o scoring less than 40%.