Full Fact’s AI Chatbots Benchmark: methodology overview
A look under the hood
OCT 15, 2026David CorneyInsights
How can we evaluate LLMs? Let us count the ways.
Trade-offs between fully-automated large-scale evaluations and smaller, human-driven evaluations
SEP 29, 2026Kate WilkinsonInsights
A decade of elections: How Full Fact AI has supported fact checkers around the world
Over the past decade, our tools have supported fact checkers by handling media monitoring during national elections across Africa to numerous elections here in the UK and referendums in Australia.
JUN 3, 2026Andy DudfieldTechnology
Trust Benchmark for LLMs
Full Fact is embarking on a multi-year project to build, test and deploy an AI Trust Benchmark for LLMs
